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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects boilerplate license-header phrases, especially the “contents of this file are subject to the terms of…” clause.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    หร
    -0.06
     AMS
    -0.06
     customize
    -0.06
     BELOW
    -0.06
    medium
    -0.06
    -volume
    -0.06
    subnet
    -0.06
    번호
    -0.06
     banner
    -0.06
     cruc
    -0.06
    POSITIVE LOGITS
    .cat
    0.07
     Dunk
    0.07
    τηκε
    0.07
     Trav
    0.07
     contents
    0.07
    investment
    0.07
     sensit
    0.07
    (enum
    0.06
    CEF
    0.06
     TextAlign
    0.06
    Act Density 0.001%

    No Known Activations