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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the spelled-out number “one.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    //
    -0.08
     peanuts
    -0.07
    osals
    -0.07
    -solving
    -0.06
    風
    -0.06
    rup
    -0.06
     histoire
    -0.06
    farm
    -0.06
    _screen
    -0.06
    sts
    -0.06
    POSITIVE LOGITS
     one
    0.13
     ONE
    0.08
     One
    0.08
     Organizer
    0.07
    .SerializeObject
    0.06
     overwritten
    0.06
     ones
    0.06
    單
    0.06
     each
    0.06
     jednoho
    0.06
    Act Density 0.042%

    No Known Activations