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

    Neuronpedia

    INDEX
    Explanations

    structured programming elements and their parameters

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

    non-affected parents and affected siblings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.51
    rungsseite
    -0.48
     noDo
    -0.47
     chi̍t
    -0.47
     Roskov
    -0.46
    ftagPool
    -0.42
    fjspx
    -0.42
     تضيفلها
    -0.42
    webElementXpaths
    -0.41
     ویکی‌پدی
    -0.38
    POSITIVE LOGITS
    doll
    0.56
     Limiting
    0.49
     Denied
    0.49
     Doll
    0.48
    kijken
    0.47
    openConnection
    0.47
     doll
    0.47
     חיצוניים
    0.46
     limiting
    0.46
     Pun
    0.45
    Act Density 0.054%

    No Known Activations