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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and structures

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

    programming keywords and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.58
    Życiorys
    -0.52
     للمعارف
    -0.50
    BufferException
    -0.46
    NameInMap
    -0.46
     dAtA
    -0.45
    Біографія
    -0.45
    Hentet
    -0.44
     kaynağından
    -0.42
     absorción
    -0.41
    POSITIVE LOGITS
    lorette
    0.43
    apolis
    0.41
    Toponymie
    0.40
    хьтан
    0.40
    NameValuePair
    0.40
    Ӕ
    0.38
    vde
    0.38
    дента
    0.38
    клопе
    0.37
    tvguidetime
    0.37
    Act Density 0.085%

    No Known Activations