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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numeric literals in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    िय
    -0.06
    .Test
    -0.06
    aphael
    -0.06
    ownership
    -0.06
     Gloria
    -0.06
     Fred
    -0.06
     keypoints
    -0.06
     Lite
    -0.06
    Cole
    -0.06
     дом
    -0.06
    POSITIVE LOGITS
    pong
    0.07
    (background
    0.07
    /year
    0.06
    Regards
    0.06
    getPage
    0.06
    irector
    0.06
    IALOG
    0.06
    TRANSFER
    0.06
     ~/.
    0.06
    _binding
    0.06
    Act Density 0.001%

    No Known Activations