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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.69
     Meksiku
    -0.66
     Dage
    -0.60
     uſ
    -0.57
    IntoConstraints
    -0.56
     Kino
    -0.54
     Theſe
    -0.54
    !!</
    -0.53
     reaſon
    -0.52
    Plots
    -0.52
    POSITIVE LOGITS
     nakalista
    0.78
     الحره
    0.54
     getItemId
    0.54
    ConverterFactory
    0.50
    例文帳に追加
    0.50
    localisation
    0.50
    шкан
    0.49
    RetentionPolicy
    0.48
     חיצוניים
    0.48
     silenzio
    0.47
    Act Density 0.133%

    No Known Activations