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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron fires on XML/HTML (or similar) markup syntax—particularly the angle-bracketed tags and their attributes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -visible
    -0.07
    ym
    -0.07
     Proto
    -0.06
    _COPY
    -0.06
    -app
    -0.06
    喜欢
    -0.06
     mActivity
    -0.06
     projectiles
    -0.06
    DownLatch
    -0.06
    .Acc
    -0.06
    POSITIVE LOGITS
     briefed
    0.07
     automobiles
    0.06
     acción
    0.06
    vál
    0.06
     aims
    0.06
    stvo
    0.06
     lors
    0.06
     Programme
    0.06
     METH
    0.06
     �
    0.06
    Act Density 0.054%

    No Known Activations