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

    Neuronpedia

    INDEX
    Explanations

    references to various prizes and awards

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

    Prize or prizes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Webcam
    -0.54
     lesbians
    -0.51
     sulfuric
    -0.50
     Shepherds
    -0.50
     Emotions
    -0.49
     hamburgers
    -0.48
     Utf
    -0.48
     Herrmann
    -0.48
     Botan
    -0.47
     vegans
    -0.47
    POSITIVE LOGITS
     Prize
    2.36
     prize
    2.33
    Prize
    2.14
     PRIZE
    2.03
    prize
    1.99
     prizes
    1.58
     Prizes
    1.56
    Prizes
    1.35
     premio
    0.94
     prêmio
    0.93
    Act Density 0.003%

    No Known Activations