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

    Neuronpedia

    INDEX
    Explanations

    stack operations

    np_max-act · gemini-2.0-flash

    The neuron fires on code identifiers that contain underscores (i.e. snake_case variable or field names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    eriod
    -0.07
    belt
    -0.07
     blog
    -0.07
    .FromSeconds
    -0.07
    ose
    -0.06
     данны
    -0.06
     Society
    -0.06
     industries
    -0.06
     CompletableFuture
    -0.06
    _Custom
    -0.06
    POSITIVE LOGITS
    θος
    0.07
    ainty
    0.06
    .GetSize
    0.06
    .VERTICAL
    0.06
     Ordered
    0.06
    kbd
    0.06
    _rb
    0.06
    _redis
    0.06
     media
    0.06
    Commands
    0.06
    Act Density 0.012%

    No Known Activations