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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отношения
    -0.07
     кат
    -0.07
    灯
    -0.06
    utra
    -0.06
    _FORM
    -0.06
     undertaking
    -0.06
     Coin
    -0.06
    ีต
    -0.06
    Detail
    -0.06
     capt
    -0.06
    POSITIVE LOGITS
     popping
    0.07
    ']=
    0.07
     redraw
    0.07
    addGap
    0.07
    Wake
    0.06
    nbsp
    0.06
    ulta
    0.06
    ews
    0.06
    "));
↵
    0.06
    Symbols
    0.06
    Act Density 0.006%

    No Known Activations