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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    This neuron detects quoted or reply-marker lines (the “>” blockquote prefixes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     seventeen
    -0.07
    acter
    -0.06
     продаж
    -0.06
     sk
    -0.06
    婷
    -0.06
     مست
    -0.06
    าด
    -0.06
    kinson
    -0.06
    :::::::::
    -0.06
     Hammond
    -0.06
    POSITIVE LOGITS
    луата
    0.06
     обрат
    0.06
    ellaneous
    0.06
    derive
    0.06
     logits
    0.06
    [Y
    0.06
     DISCLAIMER
    0.06
    ้เป
    0.06
    �
    0.06
     whatsoever
    0.06
    Act Density 0.003%

    No Known Activations