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

    Neuronpedia

    INDEX
    Explanations

    movie reviews and film-related information

    oai_token-act-pair · gemini-2.0-flash

    reviews of media

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Feedback
    -0.66
     Feedback
    -0.66
     feedback
    -0.64
    feedback
    -0.57
    FEEDBACK
    -0.55
     FEEDBACK
    -0.47
     praise
    -0.47
    star
    -0.47
    rated
    -0.47
     commentaire
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.96
    quelize
    0.76
     itſelf
    0.75
    DoubleQuotes
    0.74
    IsMutable
    0.73
    TypedDataSet
    0.73
     HasFactory
    0.72
     wireType
    0.67
     EconPapers
    0.65
     myſelf
    0.65
    Act Density 1.922%

    No Known Activations