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

    Neuronpedia

    INDEX
    Explanations

    File lists and text files

    np_max-act · gemini-2.0-flash

    This neuron fires on phrasing that describes reading (or loading) a text file—e.g. “read a text file.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     intrigued
    -0.07
    Progress
    -0.07
     uncovered
    -0.07
     Iraq
    -0.06
     confronted
    -0.06
    Mongo
    -0.06
    _predicted
    -0.06
    Occurs
    -0.06
    \Eloquent
    -0.06
    _CONTAINER
    -0.06
    POSITIVE LOGITS
    ạ
    0.07
     菲
    0.07
     누구
    0.07
     Moines
    0.07
    .......
    0.06
    мат
    0.06
    頂
    0.06
    �
    0.06
    御
    0.06
    initely
    0.06
    Act Density 0.052%

    No Known Activations