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

    Neuronpedia

    INDEX
    Explanations

    regex

    np_max-act · gemini-2.0-flash

    the neuron detects occurrences of regular-expression literals or pattern-defining syntax.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    pageNumber
    -0.07
    userId
    -0.06
    اکم
    -0.06
    zM
    -0.06
    _fm
    -0.06
    038
    -0.06
    freq
    -0.06
    .Points
    -0.06
    USH
    -0.06
    fact
    -0.06
    POSITIVE LOGITS
     admiration
    0.07
    ="__
    0.06
    _exempt
    0.06
     الحي
    0.06
     hanno
    0.06
     baking
    0.06
    …
    0.06
    」の
    0.06
     الآ
    0.06
     operative
    0.06
    Act Density 0.015%

    No Known Activations