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

    Neuronpedia

    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _YES
    -0.08
    ontvangst
    -0.07
     revital
    -0.07
     preprocessing
    -0.07
    ⵉ
    -0.07
     Revolutionary
    -0.07
    влажн
    -0.07
     routes
    -0.07
     collateral
    -0.07
     climate
    -0.07
    POSITIVE LOGITS
    �습니다
    0.07
     chain
    0.07
     Up
    0.07
    宁愿
    0.06
     kneeling
    0.06
    紧凑
    0.06
    茧
    0.06
    )(↵
    0.06
     dernier
    0.06
    0.06
    Act Density 0.001%

    No Known Activations