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

    Neuronpedia

    INDEX
    Explanations

    .decode

    np_max-act · gemini-2.0-flash

    The neuron fires on calls to decode byte‐strings into text (e.g. `.decode('utf-8')`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ホテル
    -0.07
     Tiny
    -0.06
    $mail
    -0.06
     clothes
    -0.06
    lst
    -0.06
    Tiny
    -0.06
    .scala
    -0.06
     WP
    -0.06
    <bool
    -0.06
    ITH
    -0.06
    POSITIVE LOGITS
    ุลาคม
    0.07
     canine
    0.07
    egration
    0.07
    ožná
    0.06
     abide
    0.06
    、↵↵
    0.06
     MediaType
    0.06
    د
    0.06
    え
    0.06
    _family
    0.06
    Act Density 0.002%

    No Known Activations