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

    Neuronpedia

    INDEX
    Explanations

    transcriptions/dialogues

    np_max-act · gemini-2.0-flash

    This neuron detects when a speaker is introducing themselves or giving their name.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     المتحدة
    -0.06
     Fou
    -0.06
     موتور
    -0.06
    .Float
    -0.06
    iteur
    -0.06
    itin
    -0.06
     terms
    -0.06
     высок
    -0.06
    anke
    -0.06
    -tools
    -0.06
    POSITIVE LOGITS
     lieutenant
    0.07
    (TM
    0.07
    Seg
    0.06
    SESSION
    0.06
    [left
    0.06
    (tm
    0.06
    	is
    0.06
    лся
    0.06
    [source
    0.06
    (ofSize
    0.06
    Act Density 0.059%

    No Known Activations