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

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ro
    -0.08
     عالية
    -0.07
    _WRAP
    -0.06
     Některá
    -0.06
    Fully
    -0.06
    ザイン
    -0.06
    ^(
    -0.06
    >>;↵
    -0.06
     úrov
    -0.06
    entin
    -0.06
    POSITIVE LOGITS
     oven
    0.07
    Reservation
    0.07
    bursement
    0.06
     لا
    0.06
     같이
    0.06
     �
    0.06
     ovar
    0.06
    aghan
    0.06
     descriptions
    0.06
    aken
    0.06
    Act Density 0.009%

    No Known Activations