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

    Neuronpedia

    INDEX
    Explanations

    ANY

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “ANY” (as in “ANY KIND”) in software-license boilerplate.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sect
    -0.06
     dor
    -0.06
    utedString
    -0.06
    _defs
    -0.06
     tech
    -0.06
    まず
    -0.06
    _SIMPLE
    -0.06
    .Contract
    -0.06
    addAll
    -0.06
    otes
    -0.06
    POSITIVE LOGITS
     toJson
    0.07
    'value
    0.07
    (err
    0.06
     غذ
    0.06
     insiders
    0.06
    /disc
    0.06
     spaceship
    0.06
    DebugEnabled
    0.06
     λίγ
    0.06
     Ney
    0.06
    Act Density 0.001%

    No Known Activations