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

    Neuronpedia

    INDEX
    Explanations

    belief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paused
    -0.07
     {{--<
    -0.06
     Infinite
    -0.06
    闲
    -0.06
    _KIND
    -0.06
    =open
    -0.06
    里面
    -0.06
    .notify
    -0.06
    fixed
    -0.06
    "/><
    -0.06
    POSITIVE LOGITS
    CM
    0.07
     sulfur
    0.07
     integral
    0.06
     Armor
    0.06
    pi
    0.06
    Exit
    0.06
     Gorgeous
    0.06
     يتم
    0.06
     муж
    0.06
    HAND
    0.06
    Act Density 0.002%

    No Known Activations