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

    Neuronpedia

    INDEX
    Explanations

    string length

    np_max-act · gemini-2.0-flash

    This neuron activates on parts of code containing floating‐point numeric literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ih
    -0.06
    _rad
    -0.06
    获
    -0.06
    Address
    -0.06
    روم
    -0.06
    inář
    -0.06
     bred
    -0.06
    fieldName
    -0.06
    Bas
    -0.06
    Fax
    -0.06
    POSITIVE LOGITS
    ...");↵↵
    0.07
     Guzzle
    0.07
     stereotype
    0.07
     Institutional
    0.06
    _typeof
    0.06
     verz
    0.06
     literal
    0.06
     SimpleDateFormat
    0.06
    _totals
    0.06
     comentario
    0.06
    Act Density 0.045%

    No Known Activations