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

    Neuronpedia

    INDEX
    Explanations

    measurements and sizes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    四十
    0.48
     thirty
    0.48
     चालीस
    0.48
     तीस
    0.48
    Forty
    0.46
    Thirty
    0.46
    thirty
    0.42
     Thirty
    0.42
     forty
    0.42
    ፴
    0.41
    POSITIVE LOGITS
     १६
    0.55
    8
    0.48
    textwidth
    0.48
    6
    0.47
    standard
    0.44
     ১৪
    0.43
     ১৩
    0.42
    ১৬
    0.42
     ১৬
    0.41
    7
    0.41
    Act Density 0.009%

    No Known Activations