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

    Neuronpedia

    INDEX
    Explanations

    programming/code

    np_max-act · gemini-2.0-flash

    The neuron responds to appearances of the words “property” and “claim,” e.g. in JWT‐policy contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Uncategorized
    -0.07
    _threads
    -0.06
     agre
    -0.06
    Fold
    -0.06
     kterého
    -0.06
     음악
    -0.06
     teamwork
    -0.06
     eSports
    -0.06
    HAS
    -0.06
     возраста
    -0.06
    POSITIVE LOGITS
    toInt
    0.07
     axiom
    0.07
    (def
    0.06
    巴
    0.06
    adult
    0.06
    .getSelectionModel
    0.06
     epit
    0.06
    rens
    0.06
    .onActivityResult
    0.06
    ++){
↵
    0.06
    Act Density 0.099%

    No Known Activations