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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    The neuron detects phrases indicating support or service availability times (e.g., “answers the phone at any time” or “available at all times”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ч
    -0.07
     치
    -0.07
     золот
    -0.07
    臺
    -0.07
     puppies
    -0.06
     celou
    -0.06
    /address
    -0.06
     Young
    -0.06
     Guns
    -0.06
     Suicide
    -0.06
    POSITIVE LOGITS
    -alone
    0.06
     els
    0.06
     アル
    0.06
     thereof
    0.06
    riad
    0.06
    (helper
    0.06
    [__
    0.06
    _mtx
    0.06
     inhab
    0.06
    UnitTest
    0.06
    Act Density 0.015%

    No Known Activations