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

    Neuronpedia

    INDEX
    Explanations

    periods in the text

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

    class members and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exc
    -0.43
     kamp
    -0.38
    ISupport
    -0.37
     waste
    -0.36
     valent
    -0.35
     temptation
    -0.34
    ồ
    -0.34
    ắc
    -0.33
     among
    -0.33
     encou
    -0.32
    POSITIVE LOGITS
    Personendaten
    0.94
     propOrder
    0.71
     ModelExpression
    0.70
    tagHelperRunner
    0.68
     ویکی‌پدی
    0.65
     nahilalakip
    0.61
    SharedCtor
    0.61
    SourceChecksum
    0.61
    
    0.60
     يتيمه
    0.60
    Act Density 0.004%

    No Known Activations