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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bry
    -0.07
     bł
    -0.06
     Moy
    -0.06
    integral
    -0.06
     borrowers
    -0.06
    新手
    -0.06
     Julia
    -0.06
    洋葱
    -0.06
    딲
    -0.06
    蒱
    -0.06
    POSITIVE LOGITS
    养生
    0.07
    -ag
    0.07
    这种事情
    0.07
    🍤
    0.07
    🍰
    0.07
    viar
    0.07
    分け
    0.07
    а
    0.07
     comeback
    0.07
    ónico
    0.07
    Act Density 0.010%

    No Known Activations