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

    Neuronpedia

    INDEX
    Explanations

    punctuation or formatting elements in the text

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

    Text excerpts, often quotes or citations

    np_acts-logits-general · gemini-2.0-flash

    quote introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ويكيميديا
    -0.83
     autorytatywna
    -0.82
     nahilalakip
    -0.78
    elemField
    -0.75
     المعيارى
    -0.74
     незавершена
    -0.73
    OGND
    -0.72
    WebVitals
    -0.72
     AppColors
    -0.71
     tslint
    -0.71
    POSITIVE LOGITS
    …
    1.17
    ...
    1.17
     “
    1.15
     "...
    1.14
     "
    1.12
     “…
    1.12
     ...
    1.11
     …
    1.05
    "...
    1.02
    “…
    1.00
    Act Density 0.346%

    No Known Activations