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

    Neuronpedia

    INDEX
    Explanations

    torch.nn and optim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ALLOW
    0.47
     нена
    0.39
    torch
    0.37
     kitu
    0.36
     Allowed
    0.36
    炬
    0.35
    组织的
    0.34
    senz
    0.34
    同意
    0.34
    ス
    0.34
    POSITIVE LOGITS
    optim
    0.45
     Optimize
    0.44
    nn
    0.43
     Optim
    0.42
    fft
    0.42
     fif
    0.41
     ऑप्ट
    0.41
     nn
    0.41
     pulse
    0.40
     未来
    0.40
    Act Density 0.003%

    No Known Activations