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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric literals (decimal numbers with a fractional part) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Transparent
    -0.06
     FDA
    -0.06
    ignore
    -0.06
     ⓘ
    -0.06
     Gust
    -0.06
    (Audio
    -0.06
     Sinai
    -0.06
     Fits
    -0.06
    (dialog
    -0.06
     كامل
    -0.06
    POSITIVE LOGITS
     greet
    0.07
    rift
    0.07
     actionTypes
    0.07
    toupper
    0.07
     middleware
    0.07
     yaş
    0.06
     sof
    0.06
    mise
    0.06
    timestamp
    0.06
    慧
    0.06
    Act Density 0.006%

    No Known Activations