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

    Neuronpedia

    INDEX
    Explanations

    large numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ânea
    0.57
     पांडेय
    0.55
     환
    0.55
    �
    0.54
    断面
    0.52
    يط
    0.51
     Особенно
    0.50
    ழை
    0.49
    arcía
    0.48
    úde
    0.48
    POSITIVE LOGITS
    billion
    0.73
    hereinafter
    0.68
    也将
    0.67
     உங்க
    0.67
     billion
    0.65
     trillion
    0.63
     victorious
    0.63
     blanche
    0.62
     billions
    0.61
    ලි
    0.60
    Act Density 0.000%

    No Known Activations