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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters commonly used in programming or mathematical notation

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

    citations or references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.67
    delwed
    -0.65
     désolés
    -0.55
    uxxxx
    -0.52
    OGND
    -0.50
    دانشنامهٔ
    -0.50
     незавершена
    -0.50
    GraphicsUnit
    -0.49
    تقاوى
    -0.49
     noDo
    -0.49
    POSITIVE LOGITS
    ➌
    0.47
    endpush
    0.47
    ibis
    0.45
    
    0.44
    ⎨
    0.42
    fling
    0.41
     hissing
    0.41
    alite
    0.40
    href
    0.40
    beet
    0.40
    Act Density 0.002%

    No Known Activations