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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions related to questioning one's reality or perceptions

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

    memory or mind states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.63
    httphttps
    -0.60
    OGND
    -0.56
    الإنجليزية
    -0.55
    :✨
    -0.54
    APIView
    -0.53
     insuffisamment
    -0.53
     للمعارف
    -0.52
     <<<<<<<<<<<<<<
    -0.50
    GeoNames
    -0.49
    POSITIVE LOGITS
     spelling
    0.35
    Werdegang
    0.34
    inject
    0.33
    Checkbox
    0.32
    Subtract
    0.31
     legit
    0.31
    savevideobot
    0.30
     Flexib
    0.29
     dusted
    0.29
    Reality
    0.29
    Act Density 0.027%

    No Known Activations