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

    Neuronpedia

    INDEX
    Explanations

    def

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     undermine
    -0.07
     busted
    -0.06
     Honor
    -0.06
    ?s
    -0.06
     Martin
    -0.06
     merupakan
    -0.06
    hq
    -0.06
     Democracy
    -0.06
    koliv
    -0.06
     Blanc
    -0.06
    POSITIVE LOGITS
    _PRODUCTS
    0.07
    SEARCH
    0.06
    场
    0.06
    properties
    0.06
     _____
    0.06
    .equalsIgnoreCase
    0.06
    烟
    0.06
     ******************************************************************************/↵
    0.06
    usted
    0.06
    PLAY
    0.06
    Act Density 0.027%

    No Known Activations