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

    Neuronpedia

    INDEX
    Explanations

    scientific documents

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (e.g. digits or decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Criteria
    -0.07
    .getFile
    -0.07
    Chr
    -0.06
    یزی
    -0.06
    RI
    -0.06
     Inform
    -0.06
    /questions
    -0.06
    uploads
    -0.06
    ontology
    -0.06
     Yer
    -0.06
    POSITIVE LOGITS
    _face
    0.07
    ाहक
    0.07
     oraz
    0.06
     seized
    0.06
     restTemplate
    0.06
    _Val
    0.06
     sessionFactory
    0.06
     новых
    0.06
    ()},
    0.06
     kim
    0.06
    Act Density 0.002%

    No Known Activations