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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    The neuron detects HTML tag openings (i.e. the “<” tokens that begin element tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -legged
    -0.07
    out
    -0.07
    Faculty
    -0.07
     faculty
    -0.07
     piş
    -0.07
    Regional
    -0.07
    -light
    -0.07
     department
    -0.07
     select
    -0.06
    ucu
    -0.06
    POSITIVE LOGITS
    SQLException
    0.07
    关于
    0.07
    �
    0.07
    >',
    0.06
    _optimizer
    0.06
    +",
    0.06
     пог
    0.06
    _WAKE
    0.06
    }px
    0.06
     |>
    0.06
    Act Density 0.033%

    No Known Activations