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

    Neuronpedia

    INDEX
    Explanations

    Roman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bele
    -0.07
     earm
    -0.07
     dispon
    -0.07
    歲
    -0.07
     retiring
    -0.07
    -cond
    -0.07
     betting
    -0.07
    .lbl
    -0.07
    inging
    -0.06
    疥
    -0.06
    POSITIVE LOGITS
    Mvc
    0.07
     Fan
    0.07
     makers
    0.07
    راف
    0.07
    棤
    0.07
    .codec
    0.06
    ✧
    0.06
    蓏
    0.06
    sequence
    0.06
     Про
    0.06
    Act Density 0.002%

    No Known Activations