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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    junction
    -0.07
     банку
    -0.06
    ائ
    -0.06
     повідом
    -0.06
     cracks
    -0.06
     ups
    -0.06
    _profit
    -0.06
     workflow
    -0.06
    /demo
    -0.06
     statutory
    -0.06
    POSITIVE LOGITS
    xfd
    0.06
     توسعه
    0.06
    契
    0.06
    	initialize
    0.06
     skimage
    0.06
    _sentences
    0.06
     insan
    0.06
     sexuales
    0.06
    _ATTRIB
    0.06
     slov
    0.06
    Act Density 0.009%

    No Known Activations