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

    Neuronpedia

    INDEX
    Explanations

    texting

    np_max-act · gemini-2.0-flash

    This neuron detects the “Text message:” prompt headings in the conversation formatting.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     automobiles
    -0.07
     PropertyValue
    -0.07
     violin
    -0.07
     headache
    -0.07
    	util
    -0.07
     RESET
    -0.07
    UUID
    -0.07
     Drum
    -0.06
     hilarious
    -0.06
     evapor
    -0.06
    POSITIVE LOGITS
     text
    0.08
    _codes
    0.07
     texting
    0.07
     Ack
    0.07
     aggreg
    0.07
     texts
    0.06
    cretion
    0.06
     wh
    0.06
    EXT
    0.06
    -serving
    0.06
    Act Density 0.016%

    No Known Activations