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

    Neuronpedia

    INDEX
    Explanations

    born

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens corresponding to birth years (dates in parentheses).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     siyas
    -0.07
     サ
    -0.07
     IDictionary
    -0.07
     unfavorable
    -0.07
    /png
    -0.06
     هایی
    -0.06
    YSIS
    -0.06
     blush
    -0.06
     wh
    -0.06
    xic
    -0.06
    POSITIVE LOGITS
    FOUND
    0.07
    weight
    0.06
    -number
    0.06
    (pid
    0.06
    DEPTH
    0.06
    ↵        ↵
    0.06
     CHANNEL
    0.06
    oufl
    0.06
    ="{{
    0.06
     adjustment
    0.06
    Act Density 0.003%

    No Known Activations