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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash

    The neuron responds to sentence boundary punctuation (e.g. periods, commas, and other delimiters that mark the ends of clauses or sentences).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bonuses
    -0.08
    fiber
    -0.07
    Timeout
    -0.06
    ies
    -0.06
     Helpers
    -0.06
     then
    -0.06
    USB
    -0.06
    disc
    -0.06
    encial
    -0.06
     Easy
    -0.06
    POSITIVE LOGITS
    Locator
    0.07
     QSize
    0.06
     appare
    0.06
    -fontawesome
    0.06
     защит
    0.06
     Macedonia
    0.06
     [...]↵↵
    0.06
    \Lib
    0.06
    _Enter
    0.06
    SearchParams
    0.06
    Act Density 0.041%

    No Known Activations