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

    Neuronpedia

    INDEX
    Explanations

    content restrictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    organisme
    0.41
    Estas
    0.39
     daisies
    0.38
    გენ
    0.38
     wereld
    0.38
     hexagons
    0.38
    ეხ
    0.38
     toate
    0.38
    クシー
    0.38
    لط
    0.38
    POSITIVE LOGITS
     Steve
    0.42
     Camera
    0.42
     Photo
    0.41
     Health
    0.40
     Digest
    0.40
     예
    0.40
     Plans
    0.40
     Concentration
    0.39
     Коло
    0.39
     Mobile
    0.38
    Act Density 0.001%

    No Known Activations