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

    Neuronpedia

    INDEX
    Explanations

    loop

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of hook-and-loop (e.g. Velcro) fastening systems.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Apollo
    -0.07
     LogManager
    -0.07
     insign
    -0.06
     cents
    -0.06
    (table
    -0.06
    _ATTACH
    -0.06
     mistress
    -0.06
    ch
    -0.06
    ать
    -0.06
    (dec
    -0.06
    POSITIVE LOGITS
     DataContext
    0.07
     komment
    0.06
    ();)
    0.06
    명의
    0.06
     từng
    0.06
     *))
    0.06
    ™
    0.06
    _reason
    0.06
     Lion
    0.06
    умент
    0.06
    Act Density 0.010%

    No Known Activations