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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disadv
    -0.06
     comes
    -0.06
     Hale
    -0.06
    ГО
    -0.06
    马
    -0.06
    _cookie
    -0.06
     Annie
    -0.06
     ハ
    -0.06
     influ
    -0.06
     два
    -0.06
    POSITIVE LOGITS
     обязатель
    0.07
    vl
    0.07
     MER
    0.06
    _capacity
    0.06
     detainees
    0.06
     Nội
    0.06
    嫌
    0.06
     sublicense
    0.06
    WebResponse
    0.06
     [...
    0.06
    Act Density 0.577%

    No Known Activations