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

    Neuronpedia

    INDEX
    Explanations

    Comparisons/statistics/percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibrator
    -0.07
    kB
    -0.07
    (rb
    -0.07
    到了
    -0.07
    	Thread
    -0.07
    _sequences
    -0.07
    бург
    -0.06
     unconscious
    -0.06
    :left
    -0.06
    burg
    -0.06
    POSITIVE LOGITS
     Phó
    0.07
     �
    0.06
    农业
    0.06
     HERE
    0.06
     pricey
    0.06
     nicely
    0.06
     Fred
    0.06
    กฎ
    0.06
     Bour
    0.06
    Gar
    0.06
    Act Density 0.031%

    No Known Activations