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

    Neuronpedia

    INDEX
    Explanations

    ito

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    雱
    -0.08
     emailed
    -0.07
    깡
    -0.07
    门户网站
    -0.07
    ӡ
    -0.07
    ɨ
    -0.07
    :numel
    -0.07
    asured
    -0.07
     invest
    -0.06
    涄
    -0.06
    POSITIVE LOGITS
    pearance
    0.07
     метод
    0.07
    新型
    0.07
     политик
    0.07
    WW
    0.07
     harmonic
    0.07
     prognosis
    0.07
     moderne
    0.07
     appearance
    0.07
    驱
    0.07
    Act Density 0.338%

    No Known Activations