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

    Neuronpedia

    INDEX
    Explanations

    br

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mixed
    -0.07
     mixed
    -0.06
    (express
    -0.06
    ("'
    -0.06
    (room
    -0.06
     breathing
    -0.06
    species
    -0.06
     Ernest
    -0.06
     creado
    -0.06
     briefing
    -0.06
    POSITIVE LOGITS
    _override
    0.06
     YYSTACK
    0.06
     windshield
    0.06
    genres
    0.06
     Cabinets
    0.06
    Classic
    0.06
     hats
    0.06
     elegant
    0.06
    :r
    0.06
     �
    0.06
    Act Density 0.004%

    No Known Activations