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

    Neuronpedia

    INDEX
    Explanations

    interval

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the token “interval,” especially when it’s paired with numeric or technical context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    огою
    -0.07
     orchestr
    -0.07
     GObject
    -0.07
     thaimassage
    -0.07
    토토
    -0.07
    _combo
    -0.07
     Công
    -0.07
    Fetching
    -0.07
    รง
    -0.07
    (["
    -0.06
    POSITIVE LOGITS
     interval
    0.14
     intervals
    0.12
    Interval
    0.11
    interval
    0.11
     Interval
    0.09
    ival
    0.08
     clearInterval
    0.07
    IVAL
    0.07
     equival
    0.07
     Neal
    0.07
    Act Density 0.006%

    No Known Activations