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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron is specialized in detecting numerical tokens—particularly numbers and decimal‐formatted values—throughout the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     одерж
    -0.07
     đăng
    -0.06
    Solution
    -0.06
    マ
    -0.06
    ypass
    -0.06
     �
    -0.06
     chubby
    -0.06
     same
    -0.06
     wholly
    -0.06
     fert
    -0.06
    POSITIVE LOGITS
     ->
    0.08
     ','
    0.07
     hourly
    0.07
     nám
    0.07
     Replica
    0.07
    !
    0.07
    audio
    0.07
     dollar
    0.07
     SKIP
    0.07
     数
    0.06
    Act Density 0.051%

    No Known Activations