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

    Neuronpedia

    INDEX
    Explanations

    solve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    骘
    -0.07
    תש
    -0.07
     Phar
    -0.07
     buzzing
    -0.07
     DateTime
    -0.07
    镜子
    -0.07
     Ham
    -0.07
    _heads
    -0.07
    ubb
    -0.06
    _SUP
    -0.06
    POSITIVE LOGITS
    遁
    0.07
    QUI
    0.07
    蓑
    0.07
    rien
    0.07
    .mo
    0.06
     tướng
    0.06
    	rv
    0.06
     tiện
    0.06
     InvalidOperationException
    0.06
    ивание
    0.06
    Act Density 0.020%

    No Known Activations