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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oreach
    -0.06
    .Camera
    -0.06
     Famous
    -0.06
     uçak
    -0.06
    -colored
    -0.06
     çöz
    -0.06
     partir
    -0.06
     winger
    -0.06
    ']].
    -0.06
     Japanese
    -0.06
    POSITIVE LOGITS
     своє
    0.08
     مشخص
    0.06
    ỷ
    0.06
    ğimiz
    0.06
    )*/↵
    0.06
    _imm
    0.06
    주소
    0.06
    НА
    0.06
    PointF
    0.06
    uestra
    0.06
    Act Density 0.004%

    No Known Activations