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

    Neuronpedia

    INDEX
    Explanations

    toxins released

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Пот
    -0.08
     Bour
    -0.07
    Ken
    -0.06
     Hu
    -0.06
     Hoa
    -0.06
    _CO
    -0.06
    _COLL
    -0.06
    Living
    -0.06
    伯
    -0.06
    昌
    -0.06
    POSITIVE LOGITS
     Shine
    0.07
    ::↵↵
    0.07
     Raises
    0.07
     tossing
    0.06
    ilan
    0.06
     Buyer
    0.06
    igm
    0.06
     учнів
    0.06
     ADV
    0.06
    allee
    0.06
    Act Density 0.054%

    No Known Activations