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

    Neuronpedia

    INDEX
    Explanations

    maintained

    np_max-act · gemini-2.0-flash

    The neuron detects phrases indicating that a project or package is unmaintained, deprecated, or abandoned.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _taxonomy
    -0.07
    .Cache
    -0.06
     tablet
    -0.06
     quadratic
    -0.06
    (bytes
    -0.06
    nano
    -0.06
     Blockchain
    -0.06
    (builder
    -0.06
    marca
    -0.06
    sınız
    -0.06
    POSITIVE LOGITS
     posit
    0.07
    procedure
    0.07
     rezerv
    0.06
     propensity
    0.06
    ۰
    0.06
     intens
    0.06
    _articles
    0.06
     announcing
    0.06
     tainted
    0.06
     disposed
    0.06
    Act Density 0.005%

    No Known Activations