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

    Neuronpedia

    INDEX
    Explanations

    Experimental conditions in research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Definition
    -0.07
    .definition
    -0.06
     abuse
    -0.06
    "There
    -0.06
     preset
    -0.06
     Audi
    -0.06
     학교
    -0.06
     createState
    -0.06
    血
    -0.06
    .partition
    -0.06
    POSITIVE LOGITS
     дії
    0.07
    _Begin
    0.07
    robat
    0.07
    ardon
    0.06
    idas
    0.06
    574
    0.06
     zdję
    0.06
     ترجمه
    0.06
    pagen
    0.06
    alardan
    0.06
    Act Density 0.019%

    No Known Activations