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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash

    tokens that appear at the start of a sentence or as speaker/answer labels (sentence-initial or speaker-label tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     scalable
    -0.06
     CIF
    -0.06
     unst
    -0.06
     Rover
    -0.06
    NDER
    -0.06
    ための
    -0.06
     factura
    -0.06
     onun
    -0.06
     одна
    -0.06
    ่ม
    -0.06
    POSITIVE LOGITS
    (skip
    0.06
    .?
    0.06
     ons
    0.06
    $conn
    0.06
    $.
    0.06
     карт
    0.06
    ')),↵
    0.06
    .News
    0.06
    ählen
    0.06
    $,
    0.06
    Act Density 0.039%

    No Known Activations