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

    Neuronpedia

    INDEX
    Explanations

    `self` and class initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    otipi
    0.44
    ቀም
    0.39
     newList
    0.38
     ইসলাম
    0.38
    رافی
    0.36
    toList
    0.36
    色が
    0.36
    체가
    0.36
     PRIVATE
    0.36
     menciptakan
    0.36
    POSITIVE LOGITS
     self
    0.88
    self
    0.78
     Self
    0.77
    Self
    0.76
     सेल्फ
    0.68
     SELF
    0.61
    attributes
    0.57
    自
    0.55
    SELF
    0.54
     special
    0.53
    Act Density 0.019%

    No Known Activations