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

    Neuronpedia

    INDEX
    Explanations

    import as alias

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Itoa
    0.79
    giờ
    0.78
     Các
    0.75
     stdout
    0.74
    死了
    0.73
    গর্
    0.73
     فرزند
    0.73
     INFORM
    0.72
    决策
    0.72
    ৎস্য
    0.71
    POSITIVE LOGITS
     np
    1.29
     pd
    1.28
    np
    1.27
    pd
    1.18
     pandas
    0.99
     PD
    0.97
    pandas
    0.91
    torch
    0.88
     Pandas
    0.82
    df
    0.81
    Act Density 0.348%

    No Known Activations