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

    Neuronpedia

    INDEX
    Explanations

    Barrett

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iv
    -0.07
    的愿望
    -0.06
    咋
    -0.06
     además
    -0.06
     attempts
    -0.06
    禋
    -0.06
     �
    -0.06
    conv
    -0.06
    拥
    -0.06
     \|
    -0.06
    POSITIVE LOGITS
    rence
    0.08
    ottage
    0.07
     Surrey
    0.07
     Local
    0.07
    也只是
    0.07
    ポート
    0.07
    OLEAN
    0.07
    VICE
    0.07
     директор
    0.07
    منتدي
    0.06
    Act Density 0.001%

    No Known Activations