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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ner
    -0.06
     채
    -0.06
    	Init
    -0.06
     dfs
    -0.06
    /false
    -0.06
     مناسب
    -0.06
     sem
    -0.05
     Bret
    -0.05
     continents
    -0.05
    計算
    -0.05
    POSITIVE LOGITS
     patched
    0.07
     �
    0.07
    вы
    0.07
     Adobe
    0.07
    чика
    0.06
     Madison
    0.06
    packing
    0.06
     BEL
    0.06
     offline
    0.06
     wrong
    0.06
    Act Density 0.018%

    No Known Activations