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

    Neuronpedia

    INDEX
    Explanations

    calculations or technical topics

    np_max-act · gemini-2.0-flash

    This neuron fires on the “Useful for…” lines that describe available tools and their purposes in the prompt.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     walmart
    -0.08
     Saudis
    -0.06
    soup
    -0.06
     вар
    -0.06
     Option
    -0.06
     بشر
    -0.06
    γω
    -0.06
     arteries
    -0.06
     πρό
    -0.06
    .quick
    -0.06
    POSITIVE LOGITS
    iał
    0.07
     unde
    0.06
     Sexe
    0.06
     pequ
    0.06
     stabil
    0.06
    ерж
    0.06
     signage
    0.06
     jeux
    0.06
     seguro
    0.06
     excessive
    0.06
    Act Density 0.008%

    No Known Activations