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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    The neuron activates on standalone uppercase “OR” tokens (as in “OR” in license text).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    MODULE
    -0.07
    emain
    -0.06
    وده
    -0.06
    _home
    -0.06
     AMA
    -0.06
    'I
    -0.06
    Atlantic
    -0.06
     حرفه
    -0.06
    ้ำ
    -0.06
     хими
    -0.06
    POSITIVE LOGITS
     xxx
    0.07
    (group
    0.07
     FALSE
    0.06
    _exc
    0.06
    perfil
    0.06
    OCR
    0.06
    ↵↵↵
    0.06
     toArray
    0.06
    ensis
    0.06
    _true
    0.06
    Act Density 0.001%

    No Known Activations