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

    Neuronpedia

    INDEX
    Explanations

    Movement and Progress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ewish
    -0.07
     malaria
    -0.07
     mascul
    -0.07
    咖啡
    -0.07
     isl
    -0.06
    헅
    -0.06
     hentai
    -0.06
    쎘
    -0.06
     בעיר
    -0.06
     subsidy
    -0.06
    POSITIVE LOGITS
    xs
    0.08
     Door
    0.07
    正处于
    0.07
    気になる
    0.07
    达不到
    0.07
     gs
    0.07
    /game
    0.06
     /^(
    0.06
     REC
    0.06
     תת
    0.06
    Act Density 0.045%

    No Known Activations