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

    Neuronpedia

    INDEX
    Explanations

    registering commands or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.76
    ij
    0.71
    ก
    0.70
    ي
    0.69
    س
    0.69
    ya
    0.68
    g
    0.68
     Weather
    0.68
     Raider
    0.68
     Raul
    0.65
    POSITIVE LOGITS
    τ
    0.74
    ة
    0.71
    νων
    0.71
    înes
    0.66
    lun
    0.64
    CAT
    0.64
    رسی
    0.64
    لوان
    0.64
     αυτά
    0.63
    ுள்ளார்
    0.62
    Act Density 0.003%

    No Known Activations