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

    Neuronpedia

    INDEX
    Explanations

    Parts, sections, and categories

    np_max-act · gemini-2.0-flash

    The neuron activates on enumeration markers—numbers (often followed by a period) and surrounding quote or title‐format tokens—i.e. list or section headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    heet
    -0.07
     فى
    -0.06
     την
    -0.06
     Shank
    -0.06
     invading
    -0.06
    doubleValue
    -0.06
     zombies
    -0.06
    IPC
    -0.06
    br
    -0.06
    -inc
    -0.06
    POSITIVE LOGITS
    (Error
    0.07
    _bl
    0.06
    grav
    0.06
    >{$
    0.06
    ensively
    0.06
    trait
    0.06
    @Xml
    0.06
     placed
    0.06
    руж
    0.06
     │
    0.06
    Act Density 0.014%

    No Known Activations