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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous blog content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('../../../
    -0.07
    ampions
    -0.07
     rumours
    -0.07
    	payload
    -0.06
     semua
    -0.06
    ochrome
    -0.06
    릉
    -0.06
    いた
    -0.06
    -------↵↵
    -0.06
    ẹ
    -0.06
    POSITIVE LOGITS
     sulf
    0.08
     leurs
    0.06
     وظ
    0.06
     fertil
    0.06
     maxlen
    0.06
    BarButton
    0.06
    _Class
    0.06
     Tooltip
    0.06
     merg
    0.06
     rustic
    0.06
    Act Density 0.197%

    No Known Activations