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

    Neuronpedia

    INDEX
    Explanations

    train

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ระบบ
    -0.08
     FPS
    -0.07
    บท
    -0.07
     الاجتماعي
    -0.07
    基础
    -0.07
    petto
    -0.07
     planetary
    -0.07
    .factor
    -0.07
    ff
    -0.07
     활용
    -0.07
    POSITIVE LOGITS
     приех
    0.12
     Biden
    0.09
    Stopped
    0.09
     прибы
    0.09
     sleeves
    0.09
     полностью
    0.08
     badkamer
    0.08
     atrás
    0.08
     Rain
    0.08
     Kimberly
    0.08
    Act Density 0.009%

    No Known Activations