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

    Neuronpedia

    INDEX
    Explanations

    javascript module imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    卍
    0.39
     становништво
    0.38
    =\{\
    0.38
    豕
    0.38
     Indirect
    0.38
    тись
    0.38
    ㄼ
    0.37
     ব্যবহারের
    0.37
     Notch
    0.36
     необходимо
    0.36
    POSITIVE LOGITS
    ('./
    0.86
    ("./
    0.80
    (`./
    0.71
    ('
    0.64
     './
    0.63
    ('../
    0.59
     `./
    0.59
     ./
    0.58
    ("../
    0.55
    "./
    0.54
    Act Density 0.001%

    No Known Activations