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

    Neuronpedia

    INDEX
    Explanations

    strings associated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     версию
    0.38
    ermanfaat
    0.38
     калі
    0.37
    ᕝ
    0.37
    教练
    0.37
    ндо
    0.37
    垩
    0.36
    теше
    0.36
    сторінку
    0.35
    ინისტრ
    0.35
    POSITIVE LOGITS
     aktual
    0.48
     ASSERT
    0.47
     Interpret
    0.42
     Aktual
    0.41
     ACTUAL
    0.41
     –
    0.40
     Animal
    0.40
     unused
    0.40
    ന്റെ
    0.40
     meanings
    0.39
    Act Density 0.000%

    No Known Activations