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

    Neuronpedia

    INDEX
    Explanations

    structure and style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Utilisez
    0.89
     gunakan
    0.89
     dataframe
    0.88
     utilice
    0.85
     verwenden
    0.84
     Thanos
    0.82
     sommes
    0.81
     inherits
    0.81
     ini
    0.80
     获取
    0.79
    POSITIVE LOGITS
    less
    0.77
    dow
    0.77
    transmission
    0.73
    sending
    0.72
    legen
    0.72
    ream
    0.71
    лександ
    0.70
    olver
    0.70
    <!
    0.70
    lowing
    0.69
    Act Density 0.001%

    No Known Activations