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

    Neuronpedia

    INDEX
    Explanations

    numbers (ten/twenty)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .util
    -0.07
    .NONE
    -0.07
     cables
    -0.06
    booking
    -0.06
     Bord
    -0.06
    xd
    -0.06
     kvp
    -0.06
     بيانات
    -0.06
    rowsable
    -0.06
     XmlNode
    -0.06
    POSITIVE LOGITS
    рование
    0.07
    oria
    0.07
     regimes
    0.06
     территор
    0.06
     writes
    0.06
     кры
    0.06
    ADOS
    0.06
     gái
    0.06
    акс
    0.06
    IZ
    0.06
    Act Density 0.006%

    No Known Activations