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

    Neuronpedia

    INDEX
    Explanations

    calls

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of emergency “calls” (especially 911 calls) and related service‐call contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ApiClient
    -0.07
    >:
    -0.07
     waive
    -0.06
    ↵    ↵
    -0.06
     attacking
    -0.06
    ----------------------------------------------------------------
    -0.06
    -0.06
    إ
    -0.06
     anime
    -0.06
     angry
    -0.06
    POSITIVE LOGITS
    _FEATURE
    0.07
    hton
    0.06
    πλα
    0.06
    _sold
    0.06
    -major
    0.06
     민주
    0.06
    @RunWith
    0.06
     uplift
    0.06
    خب
    0.06
     Germ
    0.06
    Act Density 0.434%

    No Known Activations