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

    Neuronpedia

    INDEX
    Explanations

    starts with "It", "You", or "company"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pointer
    0.47
     برو
    0.45
     Лей
    0.45
     бюро
    0.43
    ాయి
    0.42
     spaw
    0.42
    らない
    0.41
    仅
    0.41
     አይ
    0.39
     Боли
    0.39
    POSITIVE LOGITS
    ang
    0.47
    ikon
    0.46
    akala
    0.46
     pues
    0.45
    وأضاف
    0.45
    inicio
    0.44
    ots
    0.44
    endaten
    0.43
    iz
    0.43
    ari
    0.43
    Act Density 0.010%

    No Known Activations