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

    Neuronpedia

    INDEX
    Explanations

    references to independent testing and data to support claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    benchmarking, performance, comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.38
     démocratie
    -0.33
    -0.33
    AttributeSet
    -0.32
    ETTE
    -0.31
    ونة
    -0.31
    NewLabel
    -0.31
     patro
    -0.31
     MenuView
    -0.31
    cheiden
    -0.30
    POSITIVE LOGITS
    AndroidJUnit
    0.59
    featureID
    0.53
     comparisons
    0.52
     benchmark
    0.51
     benchmarking
    0.51
     dyno
    0.51
     Perfon
    0.51
     benchmarks
    0.50
     Comparisons
    0.50
    vidéo
    0.49
    Act Density 0.027%

    No Known Activations