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

    Neuronpedia

    INDEX
    Explanations

    emissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แก
    -0.06
     گرفته
    -0.06
     alteration
    -0.06
     Grim
    -0.06
     dzieci
    -0.06
    وير
    -0.06
    [mask
    -0.06
     сво
    -0.06
     compel
    -0.06
    _IMAGES
    -0.06
    POSITIVE LOGITS
    stdout
    0.07
     uttered
    0.07
     вип
    0.07
    ollect
    0.07
     releases
    0.07
     emitted
    0.07
     muchas
    0.07
    ical
    0.06
    lardı
    0.06
    报
    0.06
    Act Density 0.047%

    No Known Activations