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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AI
    -0.07
     evangel
    -0.07
    hud
    -0.07
    lers
    -0.06
     while
    -0.06
    *d
    -0.06
    	a
    -0.06
    enské
    -0.06
    preter
    -0.06
    )did
    -0.06
    POSITIVE LOGITS
     чис
    0.07
    ฉ
    0.07
     мест
    0.06
    tensorflow
    0.06
     according
    0.06
     Richt
    0.06
     pract
    0.06
    ュー
    0.06
    0.06
     McLaren
    0.06
    Act Density 0.002%

    No Known Activations