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

    Neuronpedia

    INDEX
    Explanations

    smoking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intro
    -0.07
     аналог
    -0.06
     اختی
    -0.06
     güç
    -0.06
     яр
    -0.06
    攻撃
    -0.06
     Levin
    -0.06
    _GL
    -0.06
    恨
    -0.06
    俊
    -0.06
    POSITIVE LOGITS
     asbestos
    0.09
     smoking
    0.08
     Tobacco
    0.07
    hma
    0.07
     ฉ
    0.07
     标
    0.07
    !',↵
    0.07
     cigarette
    0.07
    Scroll
    0.07
     Americans
    0.07
    Act Density 0.013%

    No Known Activations