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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $$$$
    -0.07
     своей
    -0.06
     bure
    -0.06
     some
    -0.06
    _ready
    -0.06
    _pop
    -0.06
     offend
    -0.06
    Some
    -0.06
    .cover
    -0.06
    _HOUR
    -0.06
    POSITIVE LOGITS
    (LOG
    0.07
    (do
    0.07
     rağmen
    0.06
     communications
    0.06
    ayscale
    0.06
     NL
    0.06
     blown
    0.06
    uso
    0.06
    _exempt
    0.06
     Alias
    0.06
    Act Density 0.003%

    No Known Activations