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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áng
    -0.07
    Filed
    -0.07
    秽
    -0.07
    mw
    -0.07
    وار
    -0.06
     pilot
    -0.06
    uge
    -0.06
    ﺠ
    -0.06
    lot
    -0.06
    第二届
    -0.06
    POSITIVE LOGITS
     dõ
    0.06
    true
    0.06
     kè
    0.06
    的要求
    0.06
     reliance
    0.06
    _fds
    0.06
    습니다
    0.06
     Ashley
    0.06
    ysi
    0.06
    회사
    0.06
    Act Density 0.001%

    No Known Activations