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

    Neuronpedia

    INDEX
    Explanations

    group

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     симптомы
    -0.07
     retailers
    -0.07
    สต
    -0.06
    PermissionsResult
    -0.06
     capable
    -0.06
    .CheckedChanged
    -0.06
     {\↵
    -0.06
     alterations
    -0.06
     багат
    -0.06
    '):
    -0.06
    POSITIVE LOGITS
    (moment
    0.06
     mockery
    0.06
    ;i
    0.06
    -leading
    0.06
     bs
    0.06
    elligent
    0.06
     committees
    0.06
    version
    0.06
    icient
    0.06
    coles
    0.06
    Act Density 0.050%

    No Known Activations