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

    Neuronpedia

    INDEX
    Explanations

    telling people things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.95
    /
    0.75
    (
    0.70
    //
    0.64
    _(
    0.63
    ،
    0.62
     =
    0.62
    0.61
     ‘
    0.61
     juga
    0.61
    POSITIVE LOGITS
     análise
    0.69
    <unused2169>
    0.68
    푥
    0.65
     يستخدم
    0.64
    푎
    0.64
     dozens
    0.61
    तोंडा
    0.61
    ள்கள்
    0.60
     يصل
    0.60
    шлай
    0.59
    Act Density 0.028%

    No Known Activations