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

    Neuronpedia

    INDEX
    Explanations

    thought

    np_max-act · gemini-2.0-flash

    The neuron flags authorial, first‐person commentary—especially phrases like “I thought,” “I decided,” or similar personal reflections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    erra
    -0.07
    adolu
    -0.07
     배송
    -0.06
     Yi
    -0.06
     الو
    -0.06
    ano
    -0.06
     Terra
    -0.06
     [↵↵
    -0.06
    RESSED
    -0.06
    ANO
    -0.06
    POSITIVE LOGITS
    (MediaType
    0.06
     Kart
    0.06
    ражд
    0.06
    .UI
    0.06
    ，或
    0.06
    bul
    0.06
     Hra
    0.06
    Sprite
    0.06
    .US
    0.06
     Search
    0.05
    Act Density 0.019%

    No Known Activations