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

    Neuronpedia

    INDEX
    Explanations

    list formatting and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    üdis
    0.45
     détour
    0.43
    addSprite
    0.43
    ссии
    0.42
    Leben
    0.42
     biss
    0.41
     católica
    0.41
    ابقات
    0.40
     śnie
    0.40
    噤
    0.40
    POSITIVE LOGITS
     percentage
    0.49
     input
    0.46
     given
    0.44
     Simplified
    0.42
     Apps
    0.42
     Beginner
    0.42
     Input
    0.41
     Percentage
    0.40
     percentages
    0.39
     gulf
    0.39
    Act Density 0.000%

    No Known Activations