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

    Neuronpedia

    INDEX
    Explanations

    code and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     long
    -0.51
    mor
    -0.50
    long
    -0.49
     fair
    -0.48
    pro
    -0.47
    ver
    -0.46
    感
    -0.45
    zk
    -0.45
    news
    -0.44
    nar
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.96
    RetentionPolicy
    0.91
     AssemblyTitle
    0.88
     nahilalakip
    0.87
    DockStyle
    0.81
     للمعارف
    0.81
    Autoritní
    0.81
     Réponses
    0.79
     myſelf
    0.78
     مشين
    0.78
    Act Density 0.006%

    No Known Activations