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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on verbs that introduce or enumerate procedural steps (e.g. “carry,” “include,” “implement,” “collect,” “deposit,” etc.), effectively flagging instructional/step-directive language.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    paypal
    -0.06
     WITH
    -0.06
    <!--[
    -0.06
     yaptı
    -0.06
     *((
    -0.06
    法院
    -0.06
    ETweet
    -0.06
     splits
    -0.06
    NEL
    -0.06
    _SIM
    -0.06
    POSITIVE LOGITS
     to
    0.14
     TO
    0.10
     To
    0.09
    -to
    0.07
     positioned
    0.07
     zakáz
    0.07
    _to
    0.07
    (mark
    0.06
     limestone
    0.06
     إلى
    0.06
    Act Density 0.193%

    No Known Activations