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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    The neuron fires on the person’s full name at the very start of a biographical entry.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    }/>
    -0.07
     Editors
    -0.07
    (click
    -0.06
     eine
    -0.06
     log
    -0.06
     cropped
    -0.06
     кноп
    -0.06
    ToF
    -0.06
    小
    -0.06
     که
    -0.06
    POSITIVE LOGITS
     odense
    0.08
    iaux
    0.06
     catches
    0.06
    BEGIN
    0.06
     dial
    0.06
    stag
    0.06
    Dé
    0.06
     reclaim
    0.06
     conex
    0.06
    cnt
    0.06
    Act Density 0.030%

    No Known Activations