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

    Neuronpedia

    INDEX
    Explanations

    hole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Invasion
    -0.08
     Women
    -0.07
    FW
    -0.07
     Hilton
    -0.07
     partnerships
    -0.07
     Renault
    -0.07
     Returns
    -0.07
    签约
    -0.07
     overweight
    -0.07
    ﯘ
    -0.07
    POSITIVE LOGITS
    	ok
    0.07
     cụ
    0.07
     בצ
    0.07
     cid
    0.07
     tslib
    0.07
    -gallery
    0.07
    中存在的
    0.07
    bay
    0.07
     при
    0.07
    чик
    0.06
    Act Density 0.003%

    No Known Activations