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

    Neuronpedia

    INDEX
    Explanations

    XML code

    np_max-act · gemini-2.0-flash

    The neuron fires on XML/HTML structural tokens—specifically opening‐tag markers (“<”), tag names (e.g. component, option, entry), and attribute names/assignment syntax inside angle brackets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ÜM
    -0.07
    ため
    -0.06
    .requestFocus
    -0.06
    該
    -0.06
    usch
    -0.06
     EGL
    -0.06
    Au
    -0.06
    �
    -0.06
     등
    -0.06
     conservative
    -0.06
    POSITIVE LOGITS
    _hosts
    0.07
     experienced
    0.07
     Terror
    0.07
     flea
    0.07
    putc
    0.07
     milit
    0.06
    éc
    0.06
     Occupational
    0.06
    lk
    0.06
     Media
    0.06
    Act Density 0.005%

    No Known Activations