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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the word “both.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fraction
    -0.06
    -automatic
    -0.06
     міль
    -0.06
    LinkedList
    -0.06
     cruc
    -0.06
    Box
    -0.06
    ολ
    -0.06
     dál
    -0.06
    •↵↵
    -0.06
    13
    -0.06
    POSITIVE LOGITS
     obou
    0.07
    bic
    0.06
    recv
    0.06
     sonucunda
    0.06
     abusive
    0.06
     updater
    0.06
    .bz
    0.06
     zprav
    0.06
     letras
    0.06
     isten
    0.06
    Act Density 0.007%

    No Known Activations