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

    Neuronpedia

    INDEX
    Explanations

    eyes and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     virtuel
    0.37
     subjective
    0.35
     idealistic
    0.34
    または
    0.34
    潛行
    0.34
     dipende
    0.33
     selecion
    0.33
     subter
    0.33
     estes
    0.32
     timeframe
    0.31
    POSITIVE LOGITS
     выгляд
    0.38
     bulldog
    0.37
    ించాడు
    0.34
     его
    0.33
     його
    0.33
     himself
    0.32
    撞
    0.32
    植物
    0.32
    ihuahua
    0.31
     把
    0.31
    Act Density 0.067%

    No Known Activations