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

    Neuronpedia

    INDEX
    Explanations

    cript

    np_max-act · gemini-2.0-flash

    HTML tags and document structure elements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects HTML structural tags—e.g. div, ul, script, noscript, and other markup elements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    WithEmail
    -0.07
    gae
    -0.07
    انگ
    -0.06
     kas
    -0.06
    indir
    -0.06
     Fakat
    -0.06
    defines
    -0.06
    lords
    -0.06
     بك
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    (int
    0.07
     signs
    0.07
    .Safe
    0.06
    .TimeUnit
    0.06
     dequeue
    0.06
     roster
    0.06
    _DELETED
    0.06
    .ToolStripItem
    0.06
     Fourier
    0.06
     hire
    0.06
    Act Density 0.005%

    No Known Activations