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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    header comments and documentation within code files.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _decode
    -0.07
     <$
    -0.07
    นคร
    -0.07
     memberId
    -0.07
    >".$
    -0.07
     centroids
    -0.07
    џџџ
    -0.06
    _CONSOLE
    -0.06
     ظ
    -0.06
    getLast
    -0.06
    POSITIVE LOGITS
     tez
    0.06
     dní
    0.06
    'nde
    0.06
     ineligible
    0.06
    Jun
    0.06
     doubted
    0.06
     accelerate
    0.06
    -note
    0.06
     Cherokee
    0.05
     eBay
    0.05
    Act Density 0.005%

    No Known Activations