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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash

    This neuron detects bibliographic citation markers and reference labels in academic text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     scape
    -0.06
    wanted
    -0.06
     nab
    -0.06
     urinary
    -0.06
    termin
    -0.06
     strap
    -0.06
     shady
    -0.06
     sinful
    -0.06
     ulus
    -0.06
     ranked
    -0.06
    POSITIVE LOGITS
     See
    0.07
    MethodBeat
    0.06
     READ
    0.06
    Від
    0.06
    .defer
    0.06
     ö
    0.06
     больш
    0.06
     ^{°}
    0.06
     LAS
    0.06
    .ReadToEnd
    0.06
    Act Density 0.001%

    No Known Activations