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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chrome
    -0.07
    .Timestamp
    -0.07
     whistle
    -0.07
    _suspend
    -0.07
    ชาย
    -0.06
     Lowell
    -0.06
    ToggleButton
    -0.06
     Uni
    -0.06
    hend
    -0.06
    ंख
    -0.06
    POSITIVE LOGITS
    [q
    0.06
    fake
    0.06
     авт
    0.06
    ?>"↵
    0.06
    writers
    0.06
     선거
    0.06
     развити
    0.06
    PLACE
    0.06
    .isfile
    0.06
    ันก
    0.06
    Act Density 0.008%

    No Known Activations