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

    Neuronpedia

    INDEX
    Explanations

    With

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يدة
    -0.07
    ออกแบบ
    -0.07
    <Address
    -0.07
     милли
    -0.07
    edis
    -0.06
     огром
    -0.06
     Leben
    -0.06
     돌아
    -0.06
    .delivery
    -0.06
     日期
    -0.06
    POSITIVE LOGITS
     beau
    0.07
    ButtonTitles
    0.06
    setState
    0.06
     dismissing
    0.06
    -he
    0.06
     прямо
    0.06
     information
    0.06
     الط
    0.06
     aud
    0.06
     yoksa
    0.06
    Act Density 0.093%

    No Known Activations