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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anol
    -0.06
    弋
    -0.06
     kp
    -0.06
    (service
    -0.06
    اث
    -0.06
     лише
    -0.06
     :(
    -0.06
    _dates
    -0.06
    骑
    -0.06
    uple
    -0.06
    POSITIVE LOGITS
    [min
    0.06
    svm
    0.06
     můj
    0.06
    erald
    0.06
     такими
    0.06
     порт
    0.06
     Від
    0.06
     ústav
    0.06
    mamış
    0.06
    vinfos
    0.06
    Act Density 0.026%

    No Known Activations