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

    Neuronpedia

    INDEX
    Explanations

    webpage dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    perm
    -0.07
    _ev
    -0.07
    �ت
    -0.06
     Stable
    -0.06
    رق
    -0.06
    .return
    -0.06
     дер
    -0.06
     ndarray
    -0.06
    <TResult
    -0.06
    .showToast
    -0.06
    POSITIVE LOGITS
    _NS
    0.06
    ким
    0.06
     seperti
    0.06
    Episode
    0.06
    equals
    0.06
    uesday
    0.06
    mıştır
    0.06
    -special
    0.06
     liberals
    0.06
    -quarter
    0.06
    Act Density 0.014%

    No Known Activations