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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash

    The neuron fires on multi‐token scientific names—especially Latin binomials of organisms and chemical compound names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     driven
    -0.07
     Sao
    -0.07
     ourselves
    -0.07
     coffee
    -0.07
    -title
    -0.07
     outros
    -0.06
     ammonia
    -0.06
     Coupe
    -0.06
     Titans
    -0.06
     SOLUTION
    -0.06
    POSITIVE LOGITS
    orianCalendar
    0.06
    ITT
    0.06
    .UInt
    0.06
    -notification
    0.06
    _SPI
    0.06
    _Clear
    0.06
    uten
    0.06
     Sı
    0.06
     affid
    0.06
    <usize
    0.06
    Act Density 0.064%

    No Known Activations