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

    Neuronpedia

    INDEX
    Explanations

    php, apex, swift, javascript code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    1.14
    t
    1.11
    er
    0.95
    +
    0.93
    (
    0.91
     that
    0.91
     for
    0.89
    ation
    0.88
     (
    0.81
    >
    0.78
    POSITIVE LOGITS
    ки
    1.08
    на
    0.88
    л
    0.86
    जनिक
    0.84
    ia
    0.81
    ন
    0.80
    ל
    0.80
    isinde
    0.79
    querySelector
    0.77
    ડિયા
    0.77
    Act Density 0.001%

    No Known Activations