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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    涤
    -0.08
    -end
    -0.07
    情報を
    -0.07
    медицинск
    -0.07
     amp
    -0.07
    찻
    -0.07
    מפק
    -0.07
    Type
    -0.07
    工程
    -0.07
     hh
    -0.07
    POSITIVE LOGITS
    拔
    0.08
    Issues
    0.07
     lol
    0.07
    estructor
    0.07
     saf
    0.07
    .ex
    0.07
     unsuccessfully
    0.07
    _truth
    0.07
     beware
    0.07
    >");
↵
    0.07
    Act Density 0.001%

    No Known Activations