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

    Neuronpedia

    INDEX
    Explanations

    w czym

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     falta
    0.42
     sepeda
    0.42
    возможно
    0.39
     Роди
    0.39
     말미암
    0.39
     Wish
    0.38
     informação
    0.38
     Salat
    0.38
     мелдеш
    0.38
     Änderungen
    0.38
    POSITIVE LOGITS
     guise
    0.49
     рамках
    0.47
     rámci
    0.47
     vicinity
    0.46
     trakcie
    0.45
     формате
    0.45
     czasie
    0.44
    ভো
    0.44
     ноябре
    0.44
     течение
    0.43
    Act Density 0.001%

    No Known Activations