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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_max-act · gemini-2.0-flash

    The neuron detects license‐related terms (e.g. substrings of “license,” “licensing,” “licenses,” “copyleft,” “GPL”) in comment headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     truy
    -0.07
     MLP
    -0.07
    ृद
    -0.06
    وس
    -0.06
    něné
    -0.06
    ith
    -0.06
    aycast
    -0.06
     LNG
    -0.06
    F
    -0.06
    ньо
    -0.06
    POSITIVE LOGITS
    /copyleft
    0.08
    acceptable
    0.07
    declar
    0.07
     singular
    0.07
     Shi
    0.07
    guard
    0.07
    (background
    0.06
    .super
    0.06
    /options
    0.06
     baş
    0.06
    Act Density 0.004%

    No Known Activations