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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leigh
    -0.38
    werp
    -0.28
    ëĬIJ
    -0.26
    RGBA
    -0.25
    reich
    -0.25
    ignon
    -0.24
    éļ¶å±ŀ
    -0.24
     ná»ģn
    -0.24
     pis
    -0.23
    åĽŀå¤į
    -0.23
    POSITIVE LOGITS
     skips
    0.30
    æĬ¥
    0.28
    гÑĢамм
    0.28
    mods
    0.27
    åīįæıIJæĺ¯
    0.27
    BP
    0.27
    UNCT
    0.26
    resh
    0.25
    kr
    0.25
    ays
    0.24
    Act Density 0.056%

    No Known Activations