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

    Neuronpedia

    INDEX
    Explanations

    Sections from diverse models

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     watched
    -0.07
    lineno
    -0.06
    獍
    -0.06
    ていく
    -0.06
    !\
    -0.06
    딫
    -0.06
    iol
    -0.06
    ERIC
    -0.06
     watchdog
    -0.06
    字样
    -0.06
    POSITIVE LOGITS
    _cons
    0.08
    ち
    0.07
     Sears
    0.07
    Implicit
    0.07
     chairs
    0.07
     Marsh
    0.07
    _imp
    0.07
    勤
    0.07
    _shuffle
    0.07
     Theta
    0.06
    Act Density 0.171%

    No Known Activations