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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash

    The neuron activates on in-text citation markers (e.g. numbered or bracketed reference/footnote indicators).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    medi
    -0.08
    gett
    -0.07
    ницт
    -0.07
    Mi
    -0.07
    roke
    -0.07
    psych
    -0.07
    maint
    -0.07
    mi
    -0.07
    نت
    -0.06
    帰
    -0.06
    POSITIVE LOGITS
    "]==
    0.07
     ]]
    0.07
     Lol
    0.07
     باشند
    0.07
    !*
    0.07
     Tear
    0.06
    ule
    0.06
    0.06
     ตำ
    0.06
     Torrent
    0.06
    Act Density 0.009%

    No Known Activations