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

    Neuronpedia

    INDEX
    Explanations

    job openings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JsonObject
    -0.07
     Hazard
    -0.07
    nutím
    -0.07
    -th
    -0.07
    鬼
    -0.06
     стати
    -0.06
    matic
    -0.06
    Pixel
    -0.06
    Root
    -0.06
     Folk
    -0.06
    POSITIVE LOGITS
    |.
    0.07
    )::
    0.07
    ------↵
    0.07
    ."]↵
    0.06
     Bd
    0.06
     sàng
    0.06
    ).
↵
    0.06
    //----------------
    0.06
    0.06
     obed
    0.06
    Act Density 0.034%

    No Known Activations