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

    Neuronpedia

    INDEX
    Explanations

    oxide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleading
    -0.08
    udiant
    -0.07
    cor
    -0.07
     plead
    -0.07
     transparency
    -0.07
    	fprintf
    -0.07
    raits
    -0.06
    Battle
    -0.06
     кам
    -0.06
    answers
    -0.06
    POSITIVE LOGITS
     MagicMock
    0.07
     ELSE
    0.07
     대통령
    0.07
    -Americans
    0.07
    機
    0.07
    红星
    0.06
    砮
    0.06
     المتحدة
    0.06
     הטבע
    0.06
    딫
    0.06
    Act Density 0.002%

    No Known Activations