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

    Neuronpedia

    INDEX
    Explanations

    patterns related to scientific and technical terms

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

    Numbers followed by exponents

    np_acts-logits-general · gemini-2.0-flash

    settling zone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -1.03
     ब्रेकडाउन
    -0.81
     queſta
    -0.80
     للمعارف
    -0.76
    iſchen
    -0.70
    цездатний
    -0.68
    DockStyle
    -0.68
    iſche
    -0.68
    NameInMap
    -0.67
    ロウィン
    -0.67
    POSITIVE LOGITS
    ↵↵
    0.35
    ↵
    0.33
    WHO
    0.33
     thôi
    0.30
    The
    0.30
     eso
    0.29
    to
    0.28
    <h3>
    0.28
    <strong>
    0.27
    Yet
    0.27
    Act Density 3.677%

    No Known Activations