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

    Neuronpedia

    INDEX
    Explanations

    ings

    np_max-act · gemini-2.0-flash

    This neuron detects Markdown table syntax elements (the ‘|’ column separators and ‘-’ header dividers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     IX
    -0.06
    Boston
    -0.06
     susceptible
    -0.06
     yoga
    -0.06
     princess
    -0.06
    157
    -0.06
     Shir
    -0.06
    Infinity
    -0.06
     Inserts
    -0.06
     interven
    -0.06
    POSITIVE LOGITS
    EndInit
    0.07
     दल
    0.07
    /application
    0.06
    _LCD
    0.06
    __↵
    0.06
     продуктов
    0.06
    된다
    0.06
     teil
    0.06
    添
    0.06
     exert
    0.06
    Act Density 0.541%

    No Known Activations