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

    Neuronpedia

    INDEX
    Explanations

    exponential growth and logarithmic scales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    传感
    0.80
     Bilbao
    0.79
    管道
    0.78
     Sorting
    0.78
     সংসদে
    0.75
    Sorting
    0.74
     pupp
    0.74
     сорта
    0.73
     Gesture
    0.73
    🪁
    0.73
    POSITIVE LOGITS
     Exponential
    1.80
     exponential
    1.74
    Exponential
    1.72
     exponencial
    1.57
    exponential
    1.53
     growth
    1.48
    growth
    1.43
    Growth
    1.41
     Growth
    1.32
    增长
    1.26
    Act Density 0.215%

    No Known Activations