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

    Neuronpedia

    INDEX
    Explanations

    numbers, zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synd
    0.66
     Woodruff
    0.65
    sorption
    0.63
     DAT
    0.63
    amer
    0.63
    ression
    0.62
    ンスター
    0.61
    ularis
    0.61
     الحض
    0.61
    یسی
    0.61
    POSITIVE LOGITS
     zero
    2.14
     Zero
    2.05
    Zero
    1.91
    zero
    1.79
     ZERO
    1.71
     cero
    1.61
    零
    1.60
     zéro
    1.58
     जीरो
    1.55
    ZERO
    1.55
    Act Density 0.598%

    No Known Activations