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

    Neuronpedia

    INDEX
    Explanations

    Math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     për
    -0.07
     różne
    -0.07
    队员
    -0.07
    xFF
    -0.07
    _major
    -0.07
    Вы
    -0.07
    اكت
    -0.07
    켄
    -0.07
     скорость
    -0.07
    ȼ
    -0.07
    POSITIVE LOGITS
     playing
    0.07
    shot
    0.07
    ':
↵
    0.07
    以下
    0.07
    toi
    0.07
    		↵	↵
    0.07
    	td
    0.07
    !
    0.06
    [W
    0.06
    ////↵
    0.06
    Act Density 0.056%

    No Known Activations