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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cha
    -0.08
    甑
    -0.07
    𐌲
    -0.06
    რ
    -0.06
    .kode
    -0.06
    -view
    -0.06
    呼吸道
    -0.06
     sponsor
    -0.06
    ng
    -0.06
    沪深
    -0.06
    POSITIVE LOGITS
     длительн
    0.08
     debacle
    0.07
    	date
    0.07
    erval
    0.07
    _EOL
    0.07
    껀
    0.07
     outcry
    0.07
    crap
    0.07
    .GetFiles
    0.07
    تح
    0.07
    Act Density 0.001%

    No Known Activations