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

    Neuronpedia

    INDEX
    Explanations

    missing something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _proba
    -0.07
    _save
    -0.07
    日报
    -0.07
     aquí
    -0.07
     Innovation
    -0.06
     큰
    -0.06
    gly
    -0.06
     هنا
    -0.06
    Conversation
    -0.06
    clicked
    -0.06
    POSITIVE LOGITS
    婕
    0.08
    诽
    0.08
    支线
    0.08
    摊
    0.07
     Dorm
    0.07
     rh
    0.07
     המשתמש
    0.07
    ствие
    0.07
    该院
    0.07
     Dịch
    0.07
    Act Density 0.072%

    No Known Activations