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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical operations and functions, particularly in code-like syntax

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

    Personendaten and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -0.43
     was
    -0.41
     this
    -0.39
     has
    -0.38
     Bard
    -0.37
    '
    -0.37
    ,
    -0.37
    ’
    -0.35
     can
    -0.35
     have
    -0.34
    POSITIVE LOGITS
     kasarigan
    0.95
     يتيمه
    0.83
    Personendaten
    0.80
     pinulongan
    0.80
    sizeCache
    0.79
     فريبيس
    0.75
     nakalista
    0.73
    +#+
    0.73
    GEBURTSDATUM
    0.72
    rungsseite
    0.71
    Act Density 3.365%

    No Known Activations