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

    Neuronpedia

    INDEX
    Explanations

    code constructs related to function calls and variable assignments

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

    Code related to exceptions or errors

    np_acts-logits-general · gemini-2.0-flash

    throw new Exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تانيه
    -1.08
    writeFieldEnd
    -1.05
     مرئيه
    -1.00
     שוליים
    -0.93
    #+#
    -0.92
    期刊论文
    -0.88
     <=",
    -0.88
     חיצוניים
    -0.86
    Tembelea
    -0.80
     चीज़ों
    -0.79
    POSITIVE LOGITS
    <eos>
    0.48
     Storia
    0.44
    جوايز
    0.43
    _
    0.39
     Staaten
    0.39
     católica
    0.39
     soluzioni
    0.38
     {
    0.38
     quiser
    0.38
     formule
    0.38
    Act Density 0.087%

    No Known Activations