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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    碼
    -0.07
    ulong
    -0.07
    تن
    -0.06
    atre
    -0.06
    質
    -0.06
     century
    -0.06
     souvenir
    -0.06
     mess
    -0.06
    ̆
    -0.06
     Official
    -0.06
    POSITIVE LOGITS
    .Google
    0.08
     GBP
    0.07
     vybav
    0.07
     Anchor
    0.07
    ━━
    0.07
     иск
    0.07
    pytest
    0.06
    izers
    0.06
    (hwnd
    0.06
    .expression
    0.06
    Act Density 0.000%

    No Known Activations