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

    Neuronpedia

    INDEX
    Explanations

    regarding

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “regarding” (as in “information regarding copyright ownership”) in license header comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    append
    -0.07
     Ampl
    -0.06
    Ger
    -0.06
     ●
    -0.06
     брос
    -0.06
    )((((
    -0.06
    .extension
    -0.06
    िलत
    -0.06
    ContainerGap
    -0.06
     Каз
    -0.06
    POSITIVE LOGITS
     regarding
    0.08
    .Theme
    0.07
    .”↵
    0.07
    Makes
    0.07
    depending
    0.07
    _Selection
    0.07
     depending
    0.06
     Collector
    0.06
     برق
    0.06
    !↵
    0.06
    Act Density 0.001%

    No Known Activations