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

    Neuronpedia

    INDEX
    Explanations

    references to advertisements and their impact or context

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

    The token "Ad" or "ad"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Ad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.68
     оригіналу
    -0.65
    CloseOperation
    -0.65
    tableFuture
    -0.64
    ResumeLayout
    -0.63
    aarrggbb
    -0.60
    Demografia
    -0.59
    RegistryLite
    -0.57
    DJANGO
    -0.57
     Lave
    -0.57
    POSITIVE LOGITS
     Ad
    0.77
     ad
    0.73
    Ad
    0.71
    ad
    0.68
     admi
    0.62
     AD
    0.61
     ads
    0.59
     Adaptation
    0.58
     hoc
    0.58
     Adrian
    0.57
    Act Density 0.051%

    No Known Activations