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

    Neuronpedia

    INDEX
    Explanations

    brackets and quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ComboBox
    -0.07
     parish
    -0.07
     uyarı
    -0.06
    关心
    -0.06
    まい
    -0.06
    臃
    -0.06
    ưở
    -0.06
    �
    -0.06
    モデル
    -0.06
    POSITIVE LOGITS
     Spread
    0.07
    )";
↵
    0.07
     מאמרים
    0.07
    론
    0.07
     Acting
    0.07
    ่น
    0.07
    盤
    0.07
    aily
    0.06
    קים
    0.06
     Payload
    0.06
    Act Density 0.023%

    No Known Activations