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

    Neuronpedia

    INDEX
    Explanations

    zero initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ዎቹ
    0.47
    রামর্শ
    0.45
     NSMutableArray
    0.43
     चालीस
    0.43
    ंच्या
    0.43
    这些
    0.42
    مكن
    0.41
     Klar
    0.41
    ్ఞ
    0.40
    धिकरण
    0.40
    POSITIVE LOGITS
     zero
    1.00
     zéro
    0.80
    zero
    0.77
     cero
    0.74
     जीरो
    0.71
     нулю
    0.70
     صفر
    0.68
    Zero
    0.66
    ゼロ
    0.66
     Zero
    0.65
    Act Density 0.172%

    No Known Activations