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

    Neuronpedia

    INDEX
    Explanations

    specific pronouns and terms indicating individuality or definition

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

    for example, alone, times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الات
    -0.32
    แดง
    -0.31
    Espèce
    -0.31
     inoxydable
    -0.31
     Administrators
    -0.31
    Související
    -0.30
     Jon
    -0.28
     when
    -0.28
     \\
    -0.28
    Iteration
    -0.28
    POSITIVE LOGITS
     ویکی‌پدی
    0.78
    WriteTagHelper
    0.70
     nakalista
    0.69
    Personendaten
    0.66
     Exacts
    0.66
     resourceCulture
    0.65
     المعيارى
    0.61
    +#+#
    0.60
    ftagPool
    0.60
     intStringLen
    0.60
    Act Density 0.088%

    No Known Activations