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

    Neuronpedia

    INDEX
    Explanations

    defects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nel
    -0.07
    assed
    -0.07
     slides
    -0.06
    走
    -0.06
    (Msg
    -0.06
    programs
    -0.06
    anje
    -0.06
     Mutex
    -0.06
     pencils
    -0.06
     secretive
    -0.06
    POSITIVE LOGITS
    imen
    0.07
    _bi
    0.07
    уючи
    0.07
     defects
    0.07
     س
    0.06
     defect
    0.06
     المملكة
    0.06
    DC
    0.06
    نی
    0.06
     особист
    0.06
    Act Density 0.006%

    No Known Activations