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

    Neuronpedia

    INDEX
    Explanations

    expose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wend
    -0.27
    usable
    -0.27
     satisf
    -0.26
    è±ģ
    -0.26
    ço
    -0.25
    .terminate
    -0.25
    kker
    -0.24
    keit
    -0.24
     extr
    -0.24
    iso
    -0.24
    POSITIVE LOGITS
     bara
    0.30
    åIJ
    0.29
    åĺ§
    0.26
    Legacy
    0.26
    éĵ¾æİ¥
    0.25
     anim
    0.24
     Meal
    0.24
    ÑĩÑĥ
    0.24
    éĥ¨ç½²
    0.24
    å°±çŁ¥éģĵ
    0.24
    Act Density 0.104%

    No Known Activations