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

    Neuronpedia

    INDEX
    Explanations

    Official

    np_max-act · gemini-2.0-flash

    The neuron fires on the formal “Official Reports” publication label in case citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rolling
    -0.07
    ении
    -0.07
    arda
    -0.07
    оу
    -0.07
     ARC
    -0.06
    илання
    -0.06
    BY
    -0.06
     Appearance
    -0.06
    illi
    -0.06
    Spark
    -0.06
    POSITIVE LOGITS
     تکن
    0.08
     stagn
    0.08
     pł
    0.07
    Spi
    0.07
    genus
    0.06
     nást
    0.06
     проп
    0.06
     quand
    0.06
    0.06
     gang
    0.06
    Act Density 0.001%

    No Known Activations