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
    -caption
    -0.07
     않는
    -0.07
    "id
    -0.07
    HeadersHeightSizeMode
    -0.07
    -service
    -0.07
    amage
    -0.07
    벤트
    -0.07
    ><!--
    -0.06
    盟
    -0.06
     philosophy
    -0.06
    POSITIVE LOGITS
     acoustic
    0.06
    _ADD
    0.06
     persu
    0.06
     وكانت
    0.06
    漫
    0.06
     vox
    0.05
     Nurs
    0.05
     Dys
    0.05
    istingu
    0.05
    autor
    0.05
    Act Density 0.013%

    No Known Activations