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

    Neuronpedia

    INDEX
    Explanations

    references to stickers and related items

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

    sticker and stickers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     H
    -0.52
     Hoff
    -0.50
    use
    -0.49
    PH
    -0.49
     time
    -0.48
     Max
    -0.48
     Hav
    -0.47
     W
    -0.46
     us
    -0.46
     Ne
    -0.46
    POSITIVE LOGITS
     Sticker
    0.94
    Sticker
    0.90
     sticker
    0.90
     stickers
    0.86
     Stickers
    0.85
    collants
    0.82
    sticker
    0.72
     pegatina
    0.71
     autocollant
    0.69
     pegatinas
    0.69
    Act Density 0.005%

    No Known Activations