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

    Neuronpedia

    INDEX
    Explanations

    code and technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    span
    -0.07
    hotel
    -0.07
     причины
    -0.07
    	elsif
    -0.07
    สำหร
    -0.07
     přeh
    -0.06
    матрива
    -0.06
     disadv
    -0.06
    _aut
    -0.06
    request
    -0.06
    POSITIVE LOGITS
     lief
    0.07
    ＼＼
    0.06
    前の
    0.06
     bozuk
    0.06
    _water
    0.06
     legislature
    0.06
     evaluated
    0.06
     Princeton
    0.06
     tumblr
    0.06
     araştırma
    0.06
    Act Density 0.000%

    No Known Activations