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

    Neuronpedia

    INDEX
    Explanations

    titles, quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mex
    -0.06
     obedient
    -0.06
     Electro
    -0.06
     Если
    -0.06
     narciss
    -0.06
    ocard
    -0.06
     McGr
    -0.06
    oksen
    -0.06
     СП
    -0.06
    MatrixXd
    -0.06
    POSITIVE LOGITS
     workshops
    0.07
    ụp
    0.07
    _uuid
    0.07
     commerc
    0.06
     flattering
    0.06
    ニュ
    0.06
    ruptcy
    0.06
     tying
    0.06
     Marvin
    0.06
    categoryId
    0.06
    Act Density 0.040%

    No Known Activations