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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Terrace
    -0.08
     서비스
    -0.07
     Blanc
    -0.07
     rt
    -0.07
    齐鲁
    -0.07
     barbecue
    -0.07
    ניס
    -0.07
     Predicate
    -0.07
     الأوروبي
    -0.06
     diện
    -0.06
    POSITIVE LOGITS
     sidew
    0.08
     @"";↵
    0.08
    蹼
    0.07
    ملاب
    0.07
    )(
    0.07
     Wy
    0.07
    ߖ
    0.07
    商業
    0.07
     corpo
    0.07
    (ball
    0.07
    Act Density 0.003%

    No Known Activations