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
     ordinal
    -0.07
    економ
    -0.07
    .norm
    -0.07
     フ
    -0.06
    iste
    -0.06
    کار
    -0.06
    ampionship
    -0.06
     gửi
    -0.06
     explanatory
    -0.06
     clipping
    -0.06
    POSITIVE LOGITS
     voyeur
    0.07
     Dress
    0.07
     ydk
    0.06
    sez
    0.06
    CppGeneric
    0.06
    Texas
    0.06
     밤
    0.06
    poi
    0.06
     YYSTYPE
    0.06
     fragmentManager
    0.06
    Act Density 0.002%

    No Known Activations