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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    This neuron detects the opening angle bracket of XML (or HTML) tags.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ROOM
    -0.07
    IOS
    -0.07
    .properties
    -0.07
    ены
    -0.07
    /signup
    -0.07
    ultipart
    -0.07
     defines
    -0.07
    (day
    -0.07
    КИ
    -0.06
     мог
    -0.06
    POSITIVE LOGITS
    ための
    0.06
    っぱ
    0.06
    잡
    0.06
    �
    0.06
    pillar
    0.06
    教学
    0.06
     передбач
    0.06
    .pageX
    0.06
     percept
    0.06
     дотрим
    0.05
    Act Density 0.001%

    No Known Activations