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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric section or list identifiers (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Steel
    -0.07
    ghi
    -0.06
    amax
    -0.06
    Infinity
    -0.06
     XL
    -0.06
    了解
    -0.06
     Stanton
    -0.06
    MED
    -0.06
     {}".
    -0.06
     yt
    -0.06
    POSITIVE LOGITS
    düm
    0.07
     Ethan
    0.07
     doğrult
    0.07
     suốt
    0.06
    (startTime
    0.06
    スポ
    0.06
     одні
    0.06
    ottle
    0.06
     Kane
    0.06
    硬
    0.06
    Act Density 0.004%

    No Known Activations