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

    Neuronpedia

    INDEX
    Explanations

    Code/Game text

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric literals (including integers and floating‐point constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Batch
    -0.08
    .pool
    -0.07
     석
    -0.07
     profound
    -0.07
    profits
    -0.06
    ＿＿
    -0.06
     transport
    -0.06
    _Buffer
    -0.06
    �
    -0.06
    ResourceManager
    -0.06
    POSITIVE LOGITS
    >↵↵
    0.06
    ateur
    0.06
     diren
    0.06
     BI
    0.06
     нее
    0.06
    ------------↵
    0.06
     tượng
    0.06
    タイプ
    0.06
    _version
    0.06
    ęp
    0.06
    Act Density 0.005%

    No Known Activations