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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gratis
    -0.07
    atik
    -0.07
    \F
    -0.06
    utton
    -0.06
    aec
    -0.06
     bbox
    -0.06
    ाथ
    -0.06
     graphical
    -0.06
     upsetting
    -0.06
     Kickstarter
    -0.06
    POSITIVE LOGITS
    CCA
    0.07
     sınav
    0.06
     сьогодні
    0.06
     Odd
    0.06
    LocalStorage
    0.06
     twenties
    0.06
    >;↵↵
    0.06
     Uint
    0.06
     minister
    0.06
    戒
    0.06
    Act Density 0.056%

    No Known Activations