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

    Neuronpedia

    INDEX
    Explanations

    encoded data/keys

    np_max-act · gemini-2.0-flash

    The neuron fires on long runs of Base64‐style characters (A–Z, a–z, 0–9, +, /, =) such as the encoded payload inside PEM blocks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    eil
    -0.08
    quets
    -0.07
    eus
    -0.07
    etí
    -0.07
    dates
    -0.06
     Ti
    -0.06
    véd
    -0.06
     bureaucracy
    -0.06
     Diet
    -0.06
    .with
    -0.06
    POSITIVE LOGITS
    Ign
    0.07
     htmlentities
    0.06
    _direction
    0.06
    阶段
    0.06
     Sự
    0.06
     CreateMap
    0.06
     intrusive
    0.06
     freezes
    0.06
     zřejmě
    0.06
    Vision
    0.06
    Act Density 0.013%

    No Known Activations