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

    Neuronpedia

    INDEX
    Explanations

    indicators of movie ratings and their classifications

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

    grades, labels, and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.77
     nahilalakip
    -0.67
    WaitGroup
    -0.66
    fromnode
    -0.66
    InitVars
    -0.65
    ніципалі
    -0.65
     كومونز
    -0.63
     EconPapers
    -0.62
    writeFieldEnd
    -0.62
     betweenstory
    -0.61
    POSITIVE LOGITS
     sauve
    0.35
    +
    0.34
    nvarchar
    0.34
     feroit
    0.33
     rêver
    0.33
     independientes
    0.32
     Contactez
    0.32
     almac
    0.32
    +/
    0.31
     sekal
    0.30
    Act Density 0.103%

    No Known Activations