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

    Neuronpedia

    INDEX
    Explanations

    calibration and measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (obj
    -0.07
    _SH
    -0.06
    ,string
    -0.06
    Ｙ
    -0.06
    yc
    -0.06
     eller
    -0.06
     theta
    -0.06
    만남
    -0.06
     принадлеж
    -0.06
     rc
    -0.06
    POSITIVE LOGITS
    cities
    0.07
    แหน
    0.07
     水
    0.07
    hrad
    0.06
    .share
    0.06
     Заг
    0.06
    looking
    0.06
     Bills
    0.06
    adem
    0.06
    odore
    0.06
    Act Density 0.046%

    No Known Activations