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

    Neuronpedia

    INDEX
    Explanations

    awards/prizes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pep
    -0.08
     Ну
    -0.07
    (comp
    -0.07
     forCell
    -0.07
     Đăng
    -0.07
    幼儿
    -0.07
    -comm
    -0.07
    -your
    -0.07
     comp
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    =j
    0.07
    äh
    0.06
     fleets
    0.06
    gpio
    0.06
    凌
    0.06
     Clara
    0.06
    roach
    0.06
     Ble
    0.06
     Fighting
    0.06
    fried
    0.06
    Act Density 0.019%

    No Known Activations