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

    Neuronpedia

    INDEX
    Explanations

    programming language import statements and class definitions

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

    local user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bemos
    -0.41
    ctivas
    -0.39
    ául
    -0.39
     Sankt
    -0.33
     colegios
    -0.33
    saraba
    -0.32
    みよう
    -0.32
    Posté
    -0.31
     Sala
    -0.31
     unethical
    -0.31
    POSITIVE LOGITS
    mobileqq
    0.89
     localObject
    0.81
     paramString
    0.66
     paramInt
    0.64
    AppMethodBeat
    0.63
     surla
    0.57
    parsedMessage
    0.56
    jsxFileName
    0.53
     indetermin
    0.50
    TypedDataSet
    0.49
    Act Density 0.026%

    No Known Activations