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

    Neuronpedia

    INDEX
    Explanations

    thoughtful and mindful demeanor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    나
    2.45
    ש
    1.98
    ೕ
    1.95
    го
    1.94
     целей
    1.91
     ря
    1.90
     penso
    1.85
    ICOS
    1.84
     πρέπει
    1.81
    عمل
    1.80
    POSITIVE LOGITS
    NewLabel
    2.73
    дентификаторы
    2.59
    ss
    2.39
    ுள்ள
    2.38
    ுள்ளது
    2.14
    CameraOpened
    2.13
    ContentType
    2.09
    tration
    2.06
    ਆਂ
    2.05
    ming
    2.03
    Act Density 0.144%

    No Known Activations