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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron detects the document’s production/proofreading header metadata (lines like “produced by… Proofreading Team at…The Internet Archive”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Το
    -0.06
     pouch
    -0.06
    ردد
    -0.06
    قام
    -0.06
     başv
    -0.06
    amer
    -0.06
    !!,
    -0.06
     Beat
    -0.06
    _TYPED
    -0.06
    řik
    -0.06
    POSITIVE LOGITS
     elle
    0.07
     spacious
    0.07
    rbrace
    0.07
    eline
    0.07
     loạt
    0.06
     grad
    0.06
     facilit
    0.06
     Less
    0.06
    .weights
    0.06
     올
    0.06
    Act Density 0.002%

    No Known Activations