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

    Neuronpedia

    INDEX
    Explanations

    legal and procedural terminology related to rules and regulations

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

    Tokens preceding enumerated lists

    np_acts-logits-general · gemini-2.0-flash

    list item identifiers like (a) and (1)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.64
    InitVars
    -0.63
     $#
    -0.59
    abestanden
    -0.59
    addCriterion
    -0.57
    oneofs
    -0.57
    oredCriteria
    -0.56
    getDescriptor
    -0.55
    adaptiveStyles
    -0.54
    pédie
    -0.52
    POSITIVE LOGITS
     i
    0.83
    i
    0.76
    a
    0.71
     ii
    0.60
    ⒜
    0.59
    ⅰ
    0.57
    ｉ
    0.57
    Ⓐ
    0.55
     مُعرِّف
    0.55
     “(
    0.53
    Act Density 0.219%

    No Known Activations