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

    Neuronpedia

    INDEX
    Explanations

    code, URLs, copyright

    np_max-act · gemini-2.0-flash

    The neuron fires on metadata definitions (version‐info, copyright, product/version blocks) in resource or header files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �어
    -0.06
    ulfilled
    -0.06
    versible
    -0.06
    راف
    -0.06
    HomeAs
    -0.06
     feas
    -0.06
    ерп
    -0.06
     Κά
    -0.06
    با
    -0.05
     playable
    -0.05
    POSITIVE LOGITS
    (#
    0.07
    _raises
    0.07
     NAT
    0.07
     aliens
    0.06
     "*
    0.06
    Lets
    0.06
    <L
    0.06
    [#
    0.06
    <*
    0.06
     Senator
    0.06
    Act Density 0.020%

    No Known Activations