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

    Neuronpedia

    INDEX
    Explanations

    fun activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ру
    1.97
    І
    1.75
    ㅠ
    1.58
    ની
    1.52
    이면
    1.50
    ре
    1.48
    ㎏
    1.47
    об
    1.45
     спокойно
    1.45
    I
    1.45
    POSITIVE LOGITS
    ções
    2.22
    lly
    1.89
    nies
    1.79
    meng
    1.79
    رير
    1.71
    ا
    1.71
     للغاية
    1.67
    ありません
    1.64
    erweise
    1.64
    ógrafo
    1.63
    Act Density 0.009%

    No Known Activations