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

    Neuronpedia

    INDEX
    Explanations

    Code/HTML symbols

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect XML/HTML-style markup tokens (angle brackets, tag names, attributes, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fs
    -0.07
     Hait
    -0.06
     onRequest
    -0.06
     gz
    -0.06
    猛
    -0.06
     nood
    -0.06
    IE
    -0.06
    Ps
    -0.06
     dil
    -0.06
    ERAL
    -0.06
    POSITIVE LOGITS
    četně
    0.07
    หลวง
    0.07
    .resources
    0.06
    proj
    0.06
    Written
    0.06
    .execute
    0.06
    ，所以
    0.06
    ックス
    0.06
     discover
    0.06
    들의
    0.06
    Act Density 0.086%

    No Known Activations