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

    Neuronpedia

    INDEX
    Explanations

    governed

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that occur in software license‐header boilerplate (e.g. the GNU/CDDL license terms and related legal wording).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pager
    -0.06
    "crypto
    -0.06
    elters
    -0.06
    iek
    -0.06
    <tr
    -0.06
    
    -0.06
    ỏ
    -0.06
    kou
    -0.05
    /tutorial
    -0.05
    emoc
    -0.05
    POSITIVE LOGITS
     GridBagConstraints
    0.08
     Military
    0.07
     Calendar
    0.06
    543
    0.06
     Rarity
    0.06
     Arth
    0.06
    FormData
    0.06
     range
    0.06
    .firebaseapp
    0.06
    dba
    0.06
    Act Density 0.001%

    No Known Activations