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

    Neuronpedia

    INDEX
    Explanations

    punctuation or symbols indicating the end of statements or sentences

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

    java console output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -1.04
     queſta
    -1.02
     مشين
    -0.98
    parsedMessage
    -0.96
     témoig
    -0.91
     indígen
    -0.90
     increí
    -0.90
    ValueStyle
    -0.90
    bootstrapcdn
    -0.90
     $_(
    -0.89
    POSITIVE LOGITS
     the
    0.54
     
    0.53
     a
    0.50
    ::
    0.46
    :
    0.45
     "
    0.45
    .
    0.43
    -
    0.43
      
    0.43
     write
    0.42
    Act Density 0.002%

    No Known Activations