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

    Neuronpedia

    INDEX
    Explanations

    references to plugins and plating in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "Pl" or "pl" followed by other letters

    np_acts-logits-general · gemini-2.0-flash

    plug, platt, plu, plate, plugin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </caption>
    -0.75
     />}
    -0.63
     مشين
    -0.63
    WriteBarrier
    -0.62
    anueva
    -0.61
    extAlignment
    -0.61
    #
    -0.60
     Sira
    -0.59
    SaveChangesAsync
    -0.58
    opposed
    -0.57
    POSITIVE LOGITS
     makl
    0.68
     PLUG
    0.60
     ventre
    0.60
    Plu
    0.58
     zabaw
    0.56
    plu
    0.54
    Билгалдахарш
    0.53
     plugins
    0.53
    ografija
    0.53
     插
    0.53
    Act Density 0.149%

    No Known Activations