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

    Neuronpedia

    INDEX
    Explanations

    el

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    2.97
    y
    2.83
    ের
    2.63
    ла
    2.63
    s
    2.59
    le
    2.50
    い
    2.19
    ي
    2.14
    k
    2.11
    ate
    2.06
    POSITIVE LOGITS
     purse
    1.59
    を有
    1.58
     hindrance
    1.50
    が高
    1.45
    Ру
    1.44
     celebrity
    1.42
    Основ
    1.41
     reaffirm
    1.41
    人材
    1.41
    ৯
    1.41
    Act Density 0.091%

    No Known Activations