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

    Neuronpedia

    INDEX
    Explanations

    python class dunder methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pigmented
    0.42
    utely
    0.41
    ர்த்த
    0.41
    gnię
    0.40
    OKA
    0.39
     குவி
    0.38
    Vik
    0.38
     খাঁ
    0.37
    URCH
    0.37
     vorticity
    0.36
    POSITIVE LOGITS
    eq
    0.91
     eq
    0.86
    repr
    0.74
     repr
    0.72
     Eq
    0.70
    Eq
    0.65
    getitem
    0.65
     EQ
    0.64
    EQ
    0.61
     represent
    0.60
    Act Density 0.012%

    No Known Activations