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

    Neuronpedia

    INDEX
    Explanations

    code/HTML tags

    np_max-act · gemini-2.0-flash

    The neuron detects the names of XML/HTML specification constants (like void, Elements, Attributes, Characters, Entities) used in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     будинку
    -0.07
    Pipeline
    -0.07
    Intialized
    -0.06
     proficiency
    -0.06
     lear
    -0.06
     chocol
    -0.06
    =null
    -0.06
    删除成功
    -0.06
    	pub
    -0.06
    елов
    -0.06
    POSITIVE LOGITS
     segreg
    0.08
     раствор
    0.07
    ريد
    0.06
     Instrument
    0.06
     Process
    0.06
     counselor
    0.06
    /em
    0.06
    -align
    0.06
     údaje
    0.06
    __[
    0.06
    Act Density 0.090%

    No Known Activations