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
    shield
    -0.06
    ۱۵
    -0.06
    .zz
    -0.06
     english
    -0.06
     English
    -0.06
     Perl
    -0.06
     GRAT
    -0.06
    etat
    -0.06
    .my
    -0.06
    _OS
    -0.06
    POSITIVE LOGITS
    Veter
    0.07
    只是
    0.07
    letics
    0.06
     い
    0.06
     сест
    0.06
    اا
    0.06
    (Layout
    0.06
    TOTAL
    0.06
    убли
    0.06
     伊
    0.06
    Act Density 0.001%

    No Known Activations