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

    Neuronpedia

    INDEX
    Explanations

    td

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    讓
    -0.07
    .free
    -0.07
     núi
    -0.06
     lexer
    -0.06
     ip
    -0.06
    เหล
    -0.06
    인
    -0.06
    让
    -0.06
     ware
    -0.06
    иться
    -0.06
    POSITIVE LOGITS
    abbrev
    0.07
     Barcl
    0.06
    puty
    0.06
     Peyton
    0.06
     Ald
    0.06
    Confirmed
    0.06
    /legal
    0.06
    addock
    0.06
     Bert
    0.06
     Saunders
    0.06
    Act Density 0.007%

    No Known Activations