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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron is specialized to spot bibliographic citation elements (publication titles, conference/journal names, years, volume/page numbers, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     هایی
    -0.07
    	volatile
    -0.07
     نوف
    -0.06
     playoff
    -0.06
     decoder
    -0.06
    umlu
    -0.06
    .dds
    -0.06
     Rohingya
    -0.06
     такими
    -0.06
    always
    -0.06
    POSITIVE LOGITS
     Ped
    0.07
    }*
    0.07
    _cn
    0.07
     schem
    0.07
     Monster
    0.06
    ログ
    0.06
    SPARENT
    0.06
    .Core
    0.06
    Scr
    0.06
     Orbit
    0.06
    Act Density 0.005%

    No Known Activations