Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical values and units of measurement within scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expressions and units

    np_acts-logits-general · gemini-2.5-flash-lite

    technical, non-prose notation—especially math expressions with numbers/operators, units and currency symbols, and reference-style citation markers in problem-like text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.52
    ğraf
    -0.52
    ContentAsync
    -0.49
     незавершена
    -0.46
    DrawerToggle
    -0.44
    SupportActionBar
    -0.44
     saites
    -0.43
    SpringBootTest
    -0.42
    ఔ
    -0.42
    ----+
    -0.41
    POSITIVE LOGITS
    astify
    0.60
     विश्वसनीयता
    0.55
     المعيارى
    0.47
    Приятного
    0.45
    (!__
    0.42
     écrans
    0.40
     zimní
    0.39
     journaux
    0.39
    äld
    0.38
    enumii
    0.37
    Act Density 21.739%

    No Known Activations