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

    Neuronpedia

    INDEX
    Explanations

    plotting/scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ъ
    -0.07
    ено
    -0.07
     Swiss
    -0.07
     черв
    -0.06
     ecl
    -0.06
     مل
    -0.06
     catal
    -0.06
     вред
    -0.06
     دن
    -0.06
    ира
    -0.06
    POSITIVE LOGITS
    iggins
    0.07
    aign
    0.07
     chương
    0.07
     `/
    0.06
     roma
    0.06
     діяль
    0.06
     LIC
    0.06
    	glm
    0.06
     XV
    0.06
    ัณฑ
    0.06
    Act Density 0.014%

    No Known Activations