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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    בחירה
    -0.06
    КА
    -0.06
    _SR
    -0.06
    外国语
    -0.06
    greso
    -0.06
    UserData
    -0.06
     Architects
    -0.06
    _assignment
    -0.06
    沁
    -0.06
    mana
    -0.06
    POSITIVE LOGITS
    Roy
    0.07
    Rated
    0.07
    界定
    0.07
     Hugh
    0.07
     своими
    0.06
    .att
    0.06
    辏
    0.06
     Boys
    0.06
     Embed
    0.06
    (gen
    0.06
    Act Density 0.078%

    No Known Activations