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

    Neuronpedia

    INDEX
    Explanations

    debugging/logs

    np_max-act · gemini-2.0-flash

    The neuron detects special structural/control tokens and metadata boundaries (e.g., header/start/end markers and similar document-level tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    .collider
    -0.07
    界
    -0.07
    cec
    -0.06
    忙
    -0.06
     kitchens
    -0.06
    ,long
    -0.06
    кур
    -0.06
    زم
    -0.06
    فاق
    -0.06
    повід
    -0.06
    POSITIVE LOGITS
     ')↵
    0.08
     PLUS
    0.07
     unwilling
    0.06
    `↵↵
    0.06
     ');↵
    0.06
    /',↵
    0.06
    (description
    0.06
     Coll
    0.06
    .depth
    0.06
     Frem
    0.06
    Act Density 0.532%

    No Known Activations