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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash

    The neuron is triggered by occurrences of “name” and its variants (named, names, naming), i.e., explicit acts of naming or identifying someone or something.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ﾑ
    -0.07
     ύ
    -0.06
     olduğu
    -0.06
     impression
    -0.06
     practical
    -0.06
    ک
    -0.06
     relics
    -0.06
     pencil
    -0.06
    _packets
    -0.06
     تل
    -0.06
    POSITIVE LOGITS
     named
    0.11
     naming
    0.10
     name
    0.08
     Naming
    0.07
     rewarded
    0.07
     unnamed
    0.07
     misses
    0.07
     Named
    0.07
    clared
    0.07
     Name
    0.06
    Act Density 0.016%

    No Known Activations