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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ف
    0.73
    quele
    0.73
    ৪
    0.72
    ו
    0.71
    א
    0.69
    ي
    0.68
    د
    0.67
    o
    0.66
    ش
    0.65
    دين
    0.64
    POSITIVE LOGITS
    st
    0.82
    stö
    0.54
    ্লাহ
    0.54
    AZ
    0.53
    ️⃣
    0.52
    ère
    0.51
    time
    0.49
     जुट
    0.49
    τερ
    0.49
    주일
    0.48
    Act Density 0.064%

    No Known Activations