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 consistently activates on numeric tokens—step numbers, time durations, and measurements—in recipe instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     neredeyse
    -0.08
    φή
    -0.07
    IGHT
    -0.06
    �
    -0.06
    /article
    -0.06
     owns
    -0.06
     Nacht
    -0.06
    Ÿ
    -0.06
    _CA
    -0.06
    وقت
    -0.06
    POSITIVE LOGITS
    рет
    0.07
    ppelin
    0.07
    MethodInfo
    0.07
     Natasha
    0.06
    toDouble
    0.06
    SenderId
    0.06
     раствор
    0.06
     TM
    0.06
    abbix
    0.06
     relaxed
    0.06
    Act Density 0.011%

    No Known Activations