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

    Neuronpedia

    INDEX
    Explanations

    product reviews

    np_max-act · gemini-2.0-flash

    The neuron activates on quantitative or measurement terms and phrases—numbers, durations, intensities, ratings, and other metrics describing strength or longevity.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     coins
    -0.07
    霞
    -0.06
     Timer
    -0.06
    611
    -0.06
    increment
    -0.06
     methodology
    -0.06
    lius
    -0.06
     iterator
    -0.06
    629
    -0.06
    teen
    -0.06
    POSITIVE LOGITS
     stare
    0.07
     สร
    0.06
    .setting
    0.06
     pří
    0.06
     doPost
    0.06
     nonetheless
    0.06
    กรรมการ
    0.06
     süre
    0.06
     emphasizing
    0.06
     unreachable
    0.06
    Act Density 0.033%

    No Known Activations