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

    Neuronpedia

    INDEX
    Explanations

    python __init__ method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clicked
    0.46
     clicked
    0.42
    furnished
    0.41
    yield
    0.40
     $)$
    0.39
    equiv
    0.39
    点击
    0.38
     assayed
    0.38
     ind
    0.38
    ="")
    0.37
    POSITIVE LOGITS
    нициа
    0.77
     инициа
    0.74
    ially
    0.73
     Init
    0.73
     initializer
    0.71
     Initializes
    0.70
     init
    0.69
    Initi
    0.68
    ilize
    0.67
     initiates
    0.66
    Act Density 0.012%

    No Known Activations