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

    Neuronpedia

    INDEX
    Explanations

    smaller

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    una
    -0.07
    しまう
    -0.06
    ,No
    -0.06
    getattr
    -0.06
     distinction
    -0.06
    =<
    -0.06
    OCK
    -0.06
    .xy
    -0.06
    สมบ
    -0.06
    }&
    -0.06
    POSITIVE LOGITS
     birlik
    0.08
     irregular
    0.06
     Arbeits
    0.06
     presumed
    0.06
     packageName
    0.06
     conviction
    0.06
    انيا
    0.06
     Armed
    0.06
    umsuz
    0.06
    [`
    0.06
    Act Density 0.010%

    No Known Activations