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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _own
    -0.07
     arranged
    -0.07
    peed
    -0.07
    як
    -0.06
    _interval
    -0.06
    WEST
    -0.06
    ensible
    -0.06
     gravel
    -0.06
    vi
    -0.06
    Republican
    -0.06
    POSITIVE LOGITS
    йн
    0.06
     ubiqu
    0.06
    /logger
    0.06
     프
    0.06
     Кри
    0.06
    ха
    0.06
    CHAR
    0.06
    菲
    0.06
     tüket
    0.06
    ,o
    0.06
    Act Density 0.037%

    No Known Activations