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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or significance

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

    comparative and superlative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.49
    astify
    -0.41
     morango
    -0.41
     leggero
    -0.38
     lâmpada
    -0.37
     esterno
    -0.35
     gebru
    -0.34
     paraître
    -0.33
     impressão
    -0.33
     halbe
    -0.33
    POSITIVE LOGITS
     AppCompatTheme
    0.68
    CodedInputStream
    0.65
    LookAnd
    0.63
    aze
    0.59
    0.56
    ConstraintMaker
    0.56
     reaſon
    0.55
    forRoot
    0.54
    Personensuche
    0.54
    帖最后由
    0.54
    Act Density 0.153%

    No Known Activations