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

    Neuronpedia

    INDEX
    Explanations

    stdlib in C code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்த
    1.49
    ो
    1.36
    ****************
    1.30
    তে
    1.28
    ことにより
    1.27
    ുടെ
    1.25
    йте
    1.25
    вання
    1.25
    о
    1.24
    ために
    1.24
    POSITIVE LOGITS
    hunters
    1.71
     πίνακα
    1.70
     পাকিস্তানকে
    1.69
     Announcement
    1.66
     rnorm
    1.64
    ESOME
    1.61
    ie
    1.60
    텟
    1.59
     dígitos
    1.59
     말투
    1.58
    Act Density 0.001%

    No Known Activations