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

    Neuronpedia

    INDEX
    Explanations

    Quotation/brackets

    np_max-act · gemini-2.0-flash

    This neuron recognizes quoted identifier names in module‐level __all__ export lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    []{↵
    -0.06
    رياض
    -0.06
     fusion
    -0.06
    RUN
    -0.06
     маст
    -0.06
     Typeface
    -0.06
    province
    -0.06
    |↵
    -0.06
    ”↵
    -0.06
     |
↵
    -0.06
    POSITIVE LOGITS
    .getNext
    0.07
    άλι
    0.07
     Info
    0.07
    алися
    0.07
     minimizing
    0.07
    (btn
    0.07
    Micro
    0.06
    nees
    0.06
    ViewHolder
    0.06
    _plus
    0.06
    Act Density 0.008%

    No Known Activations