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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or excitement

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

    Interjections or affirmations

    np_acts-logits-general · gemini-2.0-flash

    expressive sounds and interjections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -1.14
     itſelf
    -1.05
     Efq
    -1.04
    )");
    -1.02
    )";
    -1.02
     iſt
    -1.02
     ―――――
    -1.01
    $")
    -1.00
    neſs
    -1.00
     فريبيس
    -0.97
    POSITIVE LOGITS
    !
    0.79
     I
    0.77
    <eos>
    0.68
     you
    0.63
    …
    0.63
     freakin
    0.62
     freaking
    0.62
    !!!
    0.60
     Oh
    0.58
     yeah
    0.57
    Act Density 0.176%

    No Known Activations