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

    Neuronpedia

    INDEX
    Explanations

    technical/informational content

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of internal rule or policy updates, especially when presented with “new rule” phrasing and associated dates.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ún
    -0.06
    brane
    -0.06
     recursion
    -0.06
     Algorithm
    -0.06
     gev
    -0.06
     few
    -0.06
     funding
    -0.06
    _One
    -0.06
    Algorithm
    -0.06
    ाट
    -0.06
    POSITIVE LOGITS
    ('--
    0.07
    otime
    0.06
    enter
    0.06
    $array
    0.06
     lane
    0.06
    .sex
    0.06
     Cyril
    0.06
    <typename
    0.06
    	↵↵
    0.06
    jas
    0.06
    Act Density 0.003%

    No Known Activations