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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistical comparisons

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

    Percentage or ratio followed by a number

    np_acts-logits-general · gemini-2.0-flash

    percentages and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lijken
    -0.61
     yyb
    -0.61
     mergeFrom
    -0.60
     بيها
    -0.59
     conoc
    -0.58
    SourceChecksum
    -0.57
     nahilalakip
    -0.57
    setVerticalGroup
    -0.53
    tagHelperRunner
    -0.53
    évaluateur
    -0.52
    POSITIVE LOGITS
    spender
    0.58
    RefNanny
    0.54
    жели
    0.53
    CrossRef
    0.53
     enää
    0.49
     Roskov
    0.49
     newBuilder
    0.49
    それとも
    0.47
    ScopeManager
    0.47
    ANDUM
    0.46
    Act Density 0.540%

    No Known Activations