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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on XML/HTML–style markup—angle-bracketed tags and their names or attributes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sefer
    -0.08
    дут
    -0.07
     concerns
    -0.06
    رد
    -0.06
    rý
    -0.06
    Several
    -0.06
     skon
    -0.06
    both
    -0.06
     Tran
    -0.06
    ाण
    -0.06
    POSITIVE LOGITS
    >',↵
    0.09
    Angular
    0.07
    $")↵
    0.07
    SPORT
    0.07
    ]')↵
    0.07
     electrons
    0.07
    >");↵↵
    0.07
    ]")↵
    0.07
    >")↵
    0.07
    -stream
    0.07
    Act Density 0.017%

    No Known Activations