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

    Neuronpedia

    INDEX
    Explanations

    probability density

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     माइ
    0.41
     barrister
    0.41
     пари
    0.39
     জীব
    0.39
    ौसी
    0.38
     люди
    0.37
     полуо
    0.37
    律师
    0.37
     riddle
    0.37
    ャ
    0.37
    POSITIVE LOGITS
     einer
    0.39
    ogonal
    0.38
     extremely
    0.37
     unbeatable
    0.37
     kicked
    0.36
    కుండా
    0.36
     superiores
    0.35
    abies
    0.35
     correspond
    0.35
     már
    0.35
    Act Density 0.000%

    No Known Activations