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

    Neuronpedia

    INDEX
    Explanations

    Code dividers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cfg
    -0.07
     holog
    -0.06
    Args
    -0.06
    .getProperty
    -0.06
    _BASE
    -0.06
    ès
    -0.06
     sph
    -0.06
    _pb
    -0.06
     spi
    -0.06
    ета
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     ￥
    0.06
    licken
    0.06
     restructuring
    0.06
     retirees
    0.06
     организации
    0.06
    okable
    0.06
     invaluable
    0.06
    	admin
    0.06
     */↵↵↵↵
    0.06
    Act Density 0.003%

    No Known Activations