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

    Neuronpedia

    INDEX
    Explanations

    YEAR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encoding
    -0.07
    Bool
    -0.07
    Score
    -0.07
     rau
    -0.07
     Bom
    -0.06
     Super
    -0.06
     EXP
    -0.06
     derechos
    -0.06
    Jobs
    -0.06
     bakımından
    -0.06
    POSITIVE LOGITS
    rtl
    0.08
     Brill
    0.06
     rtl
    0.06
    (UINT
    0.06
    BarButtonItem
    0.06
    >>
    0.06
     RTL
    0.06
    اده
    0.06
    ((__
    0.06
    )){
    0.06
    Act Density 0.002%

    No Known Activations