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 responds to words and phrases that denote time intervals or frequencies (e.g. daily, weekly, annually, hours).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    vere
    -0.07
     Destroy
    -0.07
     ديسمبر
    -0.07
    .PI
    -0.06
    -address
    -0.06
     key
    -0.06
     Özellikle
    -0.06
    eway
    -0.06
    noinspection
    -0.06
     aDecoder
    -0.06
    POSITIVE LOGITS
    ハイ
    0.07
     кіль
    0.06
     ル
    0.06
     jPanel
    0.06
    :::::
    0.06
    _margin
    0.06
    思
    0.06
    �
    0.06
     istih
    0.05
     пох
    0.05
    Act Density 0.120%

    No Known Activations