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

    Neuronpedia

    INDEX
    Explanations

    ed

    np_max-act · gemini-2.0-flash

    This neuron detects parenthetical review citations (phrases like “(reviewed in …)”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    잖
    -0.07
     Marino
    -0.07
     posX
    -0.07
     Chow
    -0.07
    ldkf
    -0.07
     месяца
    -0.06
    603
    -0.06
     відмов
    -0.06
    BJECT
    -0.06
     Ronaldo
    -0.06
    POSITIVE LOGITS
     而
    0.07
    byter
    0.07
     ayr
    0.07
    (line
    0.06
    /><
    0.06
    cash
    0.06
     WELL
    0.06
     Народ
    0.06
     Fact
    0.06
    high
    0.06
    Act Density 0.007%

    No Known Activations