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

    Neuronpedia

    INDEX
    Explanations

    help or asking for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     После
    0.93
     பொருள
    0.83
     Гар
    0.76
    ेशन
    0.76
     Meanwhile
    0.73
    ونکي
    0.73
     Including
    0.72
     منظر
    0.71
    သော
    0.71
    သောအ
    0.70
    POSITIVE LOGITS
     بیشتری
    1.12
     پیدا
    0.97
     besar
    0.94
    دار
    0.92
    larını
    0.91
    付け
    0.90
    ளிக்க
    0.89
     داشته
    0.88
    றுத்த
    0.88
    lerini
    0.88
    Act Density 0.055%

    No Known Activations