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

    Neuronpedia

    INDEX
    Explanations

    definitions or explanations of terms

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

    refer to different meanings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Recom
    -0.46
    encodeWith
    -0.45
    ousands
    -0.44
    出版年
    -0.44
    XtraReports
    -0.43
     benchmarking
    -0.43
     forests
    -0.43
     assembled
    -0.43
     recomp
    -0.43
    RefNanny
    -0.43
    POSITIVE LOGITS
     disambiguazione
    0.49
    ChildScrollView
    0.47
    deauna
    0.43
     betekenis
    0.43
     Hinsicht
    0.41
    tellar
    0.40
    verwijspagina
    0.39
     sätt
    0.38
     contextes
    0.38
     stadig
    0.37
    Act Density 0.021%

    No Known Activations