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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сяг
    -0.07
    うち
    -0.07
    _failed
    -0.07
    是一个
    -0.07
     vidé
    -0.07
    。これ
    -0.07
    ária
    -0.06
     تبدیل
    -0.06
    侧
    -0.06
     Outcome
    -0.06
    POSITIVE LOGITS
     knows
    0.13
     knew
    0.12
     know
    0.10
     knowing
    0.09
     KNOW
    0.08
     bureaucrats
    0.08
     neurological
    0.07
     트
    0.07
     hlav
    0.06
     realizing
    0.06
    Act Density 0.030%

    No Known Activations