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

    Neuronpedia

    INDEX
    Explanations

    emphasis or strong expressions within the text

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

    citations and bracketed references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.72
    WaitGroup
    -0.65
    ----</
    -0.65
    ésultats
    -0.64
     témoig
    -0.64
    tangentMode
    -0.64
    majánló
    -0.63
    ugeot
    -0.63
     незавершена
    -0.63
    <unused8>
    -0.63
    POSITIVE LOGITS
                        
    0.40
     saying
    0.39
     JUGA
    0.39
                            
    0.38
     Grüsse
    0.36
    「
    0.35
     “
    0.35
                
    0.34
    0.33
    Saying
    0.33
    Act Density 0.030%

    No Known Activations