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

    Neuronpedia

    INDEX
    Explanations

    :* and '

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intro
    -0.07
    𝐌
    -0.07
    odus
    -0.07
     admit
    -0.06
    也算是
    -0.06
     beginner
    -0.06
     Pos
    -0.06
     hopes
    -0.06
     setIs
    -0.06
    OME
    -0.06
    POSITIVE LOGITS
    航空
    0.07
     ----------↵
    0.07
    _arguments
    0.07
    Duration
    0.07
     başka
    0.06
     outras
    0.06
    곸
    0.06
    出て
    0.06
    网站地图
    0.06
    .getFont
    0.06
    Act Density 0.001%

    No Known Activations