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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     दस
    -0.07
     Giấy
    -0.06
     shredded
    -0.06
     Plenty
    -0.06
    分享
    -0.06
    HAND
    -0.06
    	TEST
    -0.06
    ыл
    -0.06
     dị
    -0.06
     Salt
    -0.06
    POSITIVE LOGITS
    Managing
    0.07
    �
    0.07
    (chr
    0.07
     EditorGUI
    0.07
    оваться
    0.07
    ajax
    0.07
     unknow
    0.06
     wife
    0.06
    iteral
    0.06
    _BLEND
    0.06
    Act Density 0.008%

    No Known Activations