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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the double underscore pattern typically used for special methods or attributes in programming, especially in Python

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

    __be32, __u8, __be16

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    brigens
    -0.68
    IntoConstraints
    -0.60
    endphp
    -0.56
    UrlResolution
    -0.53
     يتيمه
    -0.52
     للمعارف
    -0.52
     indígen
    -0.50
    phazard
    -0.50
    TagMode
    -0.50
    inWeight
    -0.50
    POSITIVE LOGITS
    __
    0.88
    .__
    0.52
    '__
    0.45
    (__
    0.41
    "__
    0.41
     '__
    0.40
    __))
    0.39
     (__
    0.39
    <i>
    0.38
    :✨
    0.38
    Act Density 0.034%

    No Known Activations