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

    Neuronpedia

    INDEX
    Explanations

    Application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Цена
    0.58
    Seconds
    0.57
     أم
    0.57
    Hyp
    0.56
    椰
    0.56
     Ω
    0.55
    Fuente
    0.55
    Craw
    0.53
    Фото
    0.52
    Closed
    0.52
    POSITIVE LOGITS
    appcompat
    0.73
     hech
    0.65
     AppCompat
    0.64
     sapon
    0.63
     पार्षद
    0.61
     encontra
    0.58
     sava
    0.58
     наві
    0.57
    навли
    0.56
    AppCompat
    0.56
    Act Density 0.000%

    No Known Activations