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

    Neuronpedia

    INDEX
    Explanations

    Gottfried Wilhelm Leibniz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.03
    jLabel
    0.72
    ména
    0.64
    𝙪
    0.60
     Vir
    0.59
    on
    0.59
    el
    0.58
    ْن
    0.57
    atot
    0.57
     касается
    0.56
    POSITIVE LOGITS
    Attractive
    0.80
    र
    0.74
     tingkat
    0.73
    ہم
    0.69
    roasted
    0.69
     calef
    0.68
    GL
    0.66
    𝖊
    0.66
     उतने
    0.65
    தமாக
    0.65
    Act Density 0.002%

    No Known Activations