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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [date
    -0.07
    μερα
    -0.06
    現在
    -0.06
    ポート
    -0.06
    tryside
    -0.06
    REDENTIAL
    -0.06
     　　
    -0.06
    模式
    -0.06
    POP
    -0.06
    .CON
    -0.06
    POSITIVE LOGITS
     OTHER
    0.07
    ublice
    0.07
    Doug
    0.06
    净
    0.06
    (sq
    0.06
     �
    0.06
     few
    0.06
     무료
    0.06
     APPLY
    0.06
    тин
    0.06
    Act Density 0.008%

    No Known Activations