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

    Neuronpedia

    INDEX
    Explanations

    the word "only" and its variations indicating exclusivity

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

    not only but also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.56
     TextInputType
    -0.41
     BUD
    -0.39
    bibfield
    -0.39
    BibitemShut
    -0.38
     ſtate
    -0.37
    didSet
    -0.37
    bentar
    -0.37
     grades
    -0.37
     ModelRenderer
    -0.36
    POSITIVE LOGITS
    findpost
    0.56
    AnimationsModule
    0.48
    يكب
    0.48
     sposa
    0.47
    urlpatterns
    0.47
     transférez
    0.46
     mergeFrom
    0.46
    jména
    0.46
     utafitiHapana
    0.46
     فريبيس
    0.45
    Act Density 0.011%

    No Known Activations