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

    Neuronpedia

    INDEX
    Explanations

    concepts related to virtues and formal terms in various contexts

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

    terms of existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arada
    -0.35
     fréquent
    -0.34
     central
    -0.31
     früher
    -0.30
     méri
    -0.29
    entire
    -0.29
    Reino
    -0.29
     cruzado
    -0.29
     northern
    -0.29
     industry
    -0.29
    POSITIVE LOGITS
    ="@+
    0.68
    MLLoader
    0.65
     '{@
    0.63
     Catawiki
    0.58
    RTDA
    0.56
     onBind
    0.54
     kasarigan
    0.54
     mxArray
    0.53
     EconPapers
    0.53
    RTCK
    0.52
    Act Density 0.104%

    No Known Activations