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

    Neuronpedia

    INDEX
    Explanations

    ask followed by a question or topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    1.70
    स
    1.59
    ד
    1.53
    ت
    1.45
    ה
    1.45
    fect
    1.35
    iy
    1.34
    cı
    1.34
    ס
    1.30
    hc
    1.29
    POSITIVE LOGITS
    ۹
    1.40
    नून
    1.34
     modalCard
    1.30
    ﺔ
    1.30
    ありません
    1.29
     veinte
    1.29
    AR
    1.27
    ﯽ
    1.26
    AS
    1.21
     zacz
    1.21
    Act Density 0.000%

    No Known Activations