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

    Neuronpedia

    INDEX
    Explanations

    rules and restrictions

    np_max-act · gemini-2.0-flash

    technical specifications and terminology related to technology products.

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

    This neuron flags content-bearing words (longer nouns, verbs, or adjectives conveying technical details, limits, or other substantive meaning) rather than common function words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    目
    -0.07
    107
    -0.07
     Watching
    -0.06
    ա�
    -0.06
     Lens
    -0.06
     Phi
    -0.06
     Optionally
    -0.06
    üçük
    -0.06
    _lot
    -0.06
     interns
    -0.06
    POSITIVE LOGITS
    @s
    0.07
    Alamat
    0.07
    ($.
    0.07
     pretending
    0.06
    Western
    0.06
     versatile
    0.06
    @g
    0.06
     tess
    0.06
     TInt
    0.06
    routing
    0.06
    Act Density 0.033%

    No Known Activations