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

    Neuronpedia

    INDEX
    Explanations

    promise

    np_max-act · gemini-2.0-flash

    This neuron activates on the JavaScript keyword “Promise,” i.e. it detects occurrences of the term Promise in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Teaching
    -0.07
     constant
    -0.06
    struk
    -0.06
    root
    -0.06
    .cart
    -0.06
    creation
    -0.06
    _decay
    -0.06
     audiences
    -0.06
    _field
    -0.06
    AutoSize
    -0.06
    POSITIVE LOGITS
    Promise
    0.08
    InputChange
    0.07
    ρά
    0.07
     призна
    0.07
     frü
    0.07
     떨어
    0.06
    РА
    0.06
     pé
    0.06
    例
    0.06
     पक
    0.06
    Act Density 0.002%

    No Known Activations