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

    Neuronpedia

    INDEX
    Explanations

    sports statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (The
    -0.06
     Parks
    -0.06
    Seats
    -0.06
    inema
    -0.06
    _BG
    -0.06
     NBA
    -0.06
     Samantha
    -0.06
     Baghdad
    -0.06
     windy
    -0.06
     Unicorn
    -0.06
    POSITIVE LOGITS
    оля
    0.07
    -toggle
    0.07
    TPL
    0.06
     unequal
    0.06
     scientifically
    0.06
    Certainly
    0.06
     attenu
    0.06
    ющий
    0.06
     الإ
    0.06
     Sup
    0.06
    Act Density 0.019%

    No Known Activations