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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    我觉得
    -0.08
    うち
    -0.08
    directories
    -0.07
     Beitrag
    -0.07
    ibus
    -0.07
     אלא
    -0.07
    ferences
    -0.07
    cker
    -0.07
     OnClickListener
    -0.07
    Calcul
    -0.07
    POSITIVE LOGITS
    胚胎
    0.07
    Scalar
    0.07
    .extensions
    0.07
    ({
    0.07
    (percent
    0.07
    ottom
    0.07
    集体
    0.07
    _cls
    0.06
    贵族
    0.06
    sym
    0.06
    Act Density 0.140%

    No Known Activations