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

    Neuronpedia

    INDEX
    Explanations

    ()

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fak
    -0.07
     Frauen
    -0.07
    enan
    -0.06
    ena
    -0.06
     euros
    -0.06
    chest
    -0.06
    f
    -0.06
    imleri
    -0.06
     Vand
    -0.06
     Aur
    -0.06
    POSITIVE LOGITS
    VIDEO
    0.06
     ucwords
    0.06
    shape
    0.06
     清
    0.06
     Occupy
    0.06
    ư
    0.06
    ันก
    0.06
     renaming
    0.06
     ความ
    0.06
     inmate
    0.05
    Act Density 0.001%

    No Known Activations