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

    Neuronpedia

    INDEX
    Explanations

    references to different types of noise

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

    noise and its effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hebdomada
    -0.41
    tahankan
    -0.41
    DotNetBar
    -0.40
     Eagle
    -0.40
     Bec
    -0.37
     eagle
    -0.35
     oeufs
    -0.35
    runde
    -0.35
     yüzden
    -0.35
     DL
    -0.34
    POSITIVE LOGITS
     contextLoads
    0.71
    RenderAtEndOf
    0.68
     NOISE
    0.65
    ьаж
    0.64
     Noise
    0.63
     tartalomajánló
    0.60
    Noise
    0.60
    aarrggbb
    0.59
    sizeCache
    0.59
    IVEREF
    0.58
    Act Density 0.015%

    No Known Activations