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

    Neuronpedia

    INDEX
    Explanations

    advice and warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sta
    -0.06
     изуч
    -0.06
     dimin
    -0.06
    lac
    -0.06
    	body
    -0.06
    уж
    -0.06
    А
    -0.06
     parsley
    -0.06
     Negot
    -0.06
     sólo
    -0.06
    POSITIVE LOGITS
    isz
    0.07
    ueba
    0.07
    нення
    0.07
    طبيق
    0.07
    �
    0.07
    ्डल
    0.07
    /shared
    0.07
     Attribution
    0.07
    ัค
    0.06
     tabBar
    0.06
    Act Density 0.148%

    No Known Activations