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

    Neuronpedia

    INDEX
    Explanations

    self (in various languages)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     median
    -0.07
     June
    -0.07
     vào
    -0.06
     budget
    -0.06
     budgets
    -0.06
    İstanbul
    -0.06
    June
    -0.06
     considering
    -0.06
     menu
    -0.06
    Fatal
    -0.06
    POSITIVE LOGITS
    elf
    0.08
     SELF
    0.07
    自
    0.07
     self
    0.07
    аж
    0.07
    lf
    0.07
     서
    0.07
    cf
    0.07
     personalized
    0.06
    ileaks
    0.06
    Act Density 0.041%

    No Known Activations