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

    Neuronpedia

    INDEX
    Explanations

    ulus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    רד
    -0.08
     Tg
    -0.07
    .CREATE
    -0.07
     rid
    -0.07
     generation
    -0.07
    error
    -0.07
     nonlinear
    -0.07
     izraz
    -0.07
    论文
    -0.07
     Generation
    -0.07
    POSITIVE LOGITS
    기에
    0.10
    기를
    0.09
     governors
    0.08
     воздейств
    0.08
     فرمان
    0.08
     guardians
    0.08
    시에
    0.08
    sia
    0.08
    ्चर
    0.08
     gangs
    0.08
    Act Density 0.001%

    No Known Activations