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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal‐point numbers (floating-point timestamps) in source‐file header comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    imachinery
    -0.07
     Elon
    -0.06
    .matcher
    -0.06
    	nil
    -0.06
     ownerId
    -0.06
    ipc
    -0.06
     afl
    -0.06
    (stmt
    -0.06
    _subtype
    -0.06
     Georgetown
    -0.06
    POSITIVE LOGITS
    eated
    0.07
     أي
    0.06
    _deposit
    0.06
     вв
    0.06
    기의
    0.06
    产品
    0.06
    duğ
    0.06
     superiority
    0.06
     arose
    0.06
     TEMP
    0.06
    Act Density 0.007%

    No Known Activations