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

    Neuronpedia

    INDEX
    Explanations

    self-hosted or self-tuning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Сто
    0.49
    ఎ
    0.46
    ご
    0.42
    ایات
    0.41
    ईद
    0.41
     வில
    0.40
    Фи
    0.40
    こ
    0.40
    रिया
    0.39
    ορ
    0.39
    POSITIVE LOGITS
     self
    1.02
     Self
    0.95
     SELF
    0.79
    Self
    0.77
    self
    0.76
     सेल्फ
    0.70
     Selbst
    0.64
     आत्म
    0.61
     само
    0.59
     самоу
    0.59
    Act Density 0.016%

    No Known Activations