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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and technical terminology related to quantitative analysis

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

    mathematical terms and expressions

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

    mathematical notation and formula tokens (LaTeX/math expressions and other math-specific symbols/terms).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    featureID
    -0.82
     Савезне
    -0.74
    OGND
    -0.73
    ➟
    -0.69
    DoubleQuotes
    -0.64
     Administrativna
    -0.61
    InjectAttribute
    -0.56
     kaarangay
    -0.56
     linkovi
    -0.56
     препратки
    -0.55
    POSITIVE LOGITS
    TagMode
    0.46
    ↵↵
    0.42
    principalTable
    0.41
     and
    0.37
    EndInit
    0.37
    bildēt
    0.35
    KURZBESCHREIBUNG
    0.35
     Saltar
    0.35
     but
    0.34
    richTextPanel
    0.34
    Act Density 14.534%

    No Known Activations