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

    Neuronpedia

    INDEX
    Explanations

    C++ class definitions

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric literals (decimal numbers) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _DISABLE
    -0.06
     Privacy
    -0.06
     hlavou
    -0.06
     applaud
    -0.06
    .setLevel
    -0.06
    산업
    -0.06
     cruc
    -0.06
    herited
    -0.06
     Webcam
    -0.06
    semantic
    -0.06
    POSITIVE LOGITS
     stripe
    0.07
    Rightarrow
    0.07
     DISTINCT
    0.06
     zb
    0.06
    ounces
    0.06
     große
    0.06
    *(-
    0.06
    až
    0.06
    argon
    0.06
     시
    0.06
    Act Density 0.008%

    No Known Activations