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

    Neuronpedia

    INDEX
    Explanations

    such

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Request
    -0.07
    epad
    -0.07
    .Request
    -0.06
    (Card
    -0.06
     fed
    -0.06
    GameOver
    -0.06
    flare
    -0.06
     Andre
    -0.06
    .prob
    -0.06
     patent
    -0.06
    POSITIVE LOGITS
     such
    0.08
    :no
    0.07
    Tech
    0.07
     sociální
    0.07
     ~~
    0.06
    ,const
    0.06
     mq
    0.06
    Fix
    0.06
     таке
    0.06
     없었다
    0.06
    Act Density 0.013%

    No Known Activations