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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    安装
    -0.07
    рим
    -0.07
     пенс
    -0.06
    MAR
    -0.06
    Bal
    -0.06
     allergies
    -0.06
     пан
    -0.06
     PdfP
    -0.06
    Fre
    -0.06
    intel
    -0.06
    POSITIVE LOGITS
    653
    0.07
     aesthetic
    0.06
     ofstream
    0.06
    /XMLSchema
    0.06
     gender
    0.06
    .comments
    0.06
     getHeight
    0.05
    _green
    0.05
    _WORD
    0.05
    /search
    0.05
    Act Density 0.005%

    No Known Activations