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

    Neuronpedia

    INDEX
    Explanations

    machine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LOOK
    -0.08
    UTF
    -0.08
     LB
    -0.07
    urf
    -0.07
    _optional
    -0.07
    وم
    -0.07
    ون
    -0.07
    辅导
    -0.07
    TOTAL
    -0.07
    _LOADING
    -0.07
    POSITIVE LOGITS
    机
    0.08
     machine
    0.08
    .machine
    0.07
    〵
    0.07
     Junction
    0.07
    جريمة
    0.07
     då
    0.07
     selves
    0.07
     Machines
    0.07
    启发
    0.07
    Act Density 0.022%

    No Known Activations