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

    Neuronpedia

    INDEX
    Explanations

    Code/Configuration

    np_max-act · gemini-2.0-flash

    The neuron activates on pieces of CamelCase or PascalCase identifiers in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Legendary
    -0.08
    holes
    -0.07
     Vulkan
    -0.07
    init
    -0.07
    ibrate
    -0.06
     CR
    -0.06
     kin
    -0.06
    _PM
    -0.06
    Ordinal
    -0.06
    apsible
    -0.06
    POSITIVE LOGITS
     wires
    0.06
     isOpen
    0.06
    ENSE
    0.06
     حفظ
    0.06
    CHOOL
    0.05
    _ASSUME
    0.05
    فن
    0.05
    ło
    0.05
    角
    0.05
    .Then
    0.05
    Act Density 0.111%

    No Known Activations