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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Api
    -0.07
    ublisher
    -0.06
     Cheap
    -0.06
     flirting
    -0.06
    ulant
    -0.06
    Abr
    -0.06
     людям
    -0.06
     referencia
    -0.06
    finite
    -0.06
    说明
    -0.06
    POSITIVE LOGITS
    、二
    0.08
    >'.
    0.08
     forecasting
    0.07
     ER
    0.07
    .getHours
    0.06
    볼
    0.06
     preseason
    0.06
     kern
    0.06
     tet
    0.06
    .Border
    0.06
    Act Density 0.002%

    No Known Activations