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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash

    references to medical conditions related to cardiovascular health.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is triggered by floating‐point number tokens (i.e. decimal numbers with many digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     endeavor
    -0.06
    Grow
    -0.06
     Same
    -0.06
     Stay
    -0.06
     Adding
    -0.06
     equivalent
    -0.06
    "These
    -0.06
    .take
    -0.06
     dentist
    -0.06
     linebacker
    -0.06
    POSITIVE LOGITS
    ού
    0.07
     ################################################
    0.07
    フ
    0.07
    ecret
    0.06
     منت
    0.06
    Ы
    0.06
     СП
    0.06
     "\\
    0.06
     #{@
    0.06
     sağlıklı
    0.06
    Act Density 0.002%

    No Known Activations