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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acus
    -0.06
     Blow
    -0.06
    atonin
    -0.06
    irus
    -0.06
    cus
    -0.06
     polygons
    -0.06
    厂
    -0.06
    Goods
    -0.06
    881
    -0.06
    ("");↵
    -0.06
    POSITIVE LOGITS
     newer
    0.06
     tổng
    0.06
    ARSER
    0.06
     detalle
    0.06
     Kı
    0.06
     annon
    0.06
     mine
    0.06
     vale
    0.06
     eager
    0.06
    Quite
    0.06
    Act Density 0.056%

    No Known Activations