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

    Neuronpedia

    INDEX
    Explanations

    instances of special characters or formatting in the text

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

    currency codes and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.96
     ModelExpression
    -0.92
     فريبيس
    -0.88
    ьажоргаш
    -0.88
     betweenstory
    -0.87
     témoig
    -0.81
     ſeine
    -0.81
    <unused52>
    -0.80
    <pad>
    -0.80
    <unused14>
    -0.79
    POSITIVE LOGITS
    ,
    0.36
     
    0.34
    .
    0.32
     --
    0.30
    1
    0.30
    :
    0.29
    --
    0.28
    FL
    0.28
     -
    0.27
    PT
    0.27
    Act Density 0.002%

    No Known Activations