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

    Neuronpedia

    INDEX
    Explanations

    template blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ća
    0.81
    ים
    0.76
    ی
    0.70
    ناك
    0.70
    s
    0.69
     فقط
    0.68
    rogens
    0.67
    ována
    0.67
    س
    0.66
     nélkül
    0.65
    POSITIVE LOGITS
    ।
    0.86
    ة
    0.77
    ید
    0.75
    。
    0.73
    </h2>
    0.71
    ли
    0.70
    Ab
    0.66
     and
    0.65
     in
    0.64
    িং
    0.64
    Act Density 0.000%

    No Known Activations