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

    Neuronpedia

    INDEX
    Explanations

    percentages and proportions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uluh
    0.45
    äus
    0.44
    amélioration
    0.44
     improve
    0.44
    jä
    0.44
     улуч
    0.42
    šanas
    0.41
     짧
    0.41
     mejoras
    0.40
     doubles
    0.40
    POSITIVE LOGITS
    占比
    1.06
     proportion
    1.03
     percentage
    0.92
     percentages
    0.92
    proportion
    0.88
     proportions
    0.87
     pourcentage
    0.87
    大部分
    0.86
     porcentaje
    0.85
     predominance
    0.84
    Act Density 0.215%

    No Known Activations