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

    Neuronpedia

    INDEX
    Explanations

    words related to names and acknowledgments

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

    ending in "ck" or containing "Sand"

    np_acts-logits-general · gemini-2.0-flash

    names ending in ick or ack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.75
    <%=
    -0.74
    Przypisy
    -0.63
    IsMutable
    -0.62
     Schulte
    -0.62
     BorderRadius
    -0.62
    ="#"><
    -0.61
    بوابة
    -0.60
     Sera
    -0.60
    phrine
    -0.59
    POSITIVE LOGITS
     lick
    0.64
    ety
    0.61
    ting
    0.60
     Nick
    0.58
    Buck
    0.58
    ering
    0.57
     Chick
    0.56
     Buck
    0.56
     Jad
    0.56
    ์
    0.55
    Act Density 0.160%

    No Known Activations