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

    Neuronpedia

    INDEX
    Explanations

    Programming/logic

    np_max-act · gemini-2.0-flash

    objects and their quantities in relational contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects placeholder variable identifiers and their components (e.g. “NAME”, “_”, and digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Plug
    -0.07
     SAT
    -0.07
    puty
    -0.07
     zipcode
    -0.06
    King
    -0.06
    ALK
    -0.06
    DataReader
    -0.06
    」と
    -0.06
     sale
    -0.06
    :::
    -0.06
    POSITIVE LOGITS
     количество
    0.08
    difference
    0.06
     пре
    0.06
    semi
    0.06
    ателя
    0.06
    —
    0.06
     Dani
    0.06
    ินด
    0.06
     Yorkshire
    0.06
     Forward
    0.06
    Act Density 0.046%

    No Known Activations