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

    Neuronpedia

    INDEX
    Explanations

    supported formats

    np_acts-logits-general · gemini-2.5-flash-lite

    shape

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and numerical/quantitative information such as statistics, metrics, dates, and monetary values.

    oai_token-act-pair · claude-4-5-haikuTriggered by @tatsatx
    New Auto-Interp
    Negative Logits
     ise
    0.09
    ,
    0.09
     y
    0.09
     à
    0.09
     якобы
    0.09
     Amt
    0.08
     u
    0.08
     tonight
    0.08
     Phuket
    0.08
    ডস
    0.08
    POSITIVE LOGITS
    abhavena
    0.09
    BOOLE
    0.08
    enumer
    0.08
    スイッチ
    0.08
    strtotime
    0.08
     ಅಮ
    0.08
     डिप्ट
    0.08
    鳳
    0.08
    totime
    0.08
    phenoxymethyl
    0.08
    Act Density 7.454%

    No Known Activations