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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ایه
    -0.07
     deserves
    -0.06
     교수
    -0.06
    assel
    -0.06
     wants
    -0.06
    获
    -0.06
    Delimiter
    -0.06
     Wade
    -0.06
     Agile
    -0.06
    _rl
    -0.06
    POSITIVE LOGITS
    shutdown
    0.08
     civilian
    0.07
     coffee
    0.06
     poke
    0.06
    Man
    0.06
    bid
    0.06
     mozilla
    0.06
     iPad
    0.06
    urface
    0.06
    自己的
    0.06
    Act Density 0.015%

    No Known Activations