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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation

    np_max-act · gemini-2.0-flash

    The neuron mainly fires on the little floating‐point numbers (the decimal activation values) that appear inside table cells.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ۱۳
    -0.08
    .xxx
    -0.07
     coke
    -0.07
    participant
    -0.06
    accumulate
    -0.06
    asant
    -0.06
    _frontend
    -0.06
     entr
    -0.06
    maintenance
    -0.06
    Five
    -0.06
    POSITIVE LOGITS
     organ
    0.06
     Cs
    0.06
     Greeks
    0.06
     đột
    0.06
     так
    0.06
    _instruction
    0.06
     integ
    0.06
     mesmo
    0.06
     Ό
    0.06
    aporan
    0.06
    Act Density 0.037%

    No Known Activations