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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (integer and floating-point numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _adc
    -0.07
    alers
    -0.07
    thinking
    -0.07
     Yani
    -0.06
     भ
    -0.06
    /Base
    -0.06
    �
    -0.06
    .Geometry
    -0.06
    やる夫
    -0.06
    ρος
    -0.06
    POSITIVE LOGITS
    ลา
    0.08
     prag
    0.06
    \:
    0.06
    scss
    0.06
     【
    0.06
    /grid
    0.06
    ruby
    0.06
    -effective
    0.06
     Gü
    0.06
    ?>↵↵↵
    0.06
    Act Density 0.019%

    No Known Activations