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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    对他们
    -0.08
    얜
    -0.07
    _HELP
    -0.07
    UCH
    -0.07
     Bags
    -0.07
     Context
    -0.07
    Semantic
    -0.06
    ważnie
    -0.06
     furry
    -0.06
     TELE
    -0.06
    POSITIVE LOGITS
    =YES
    0.08
    网站地图
    0.08
    _mapper
    0.07
    可以在
    0.07
     origin
    0.07
     الص
    0.07
     increased
    0.07
     rebuild
    0.06
    &B
    0.06
     plat
    0.06
    Act Density 0.000%

    No Known Activations