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

    Neuronpedia

    INDEX
    Explanations

    repeated patterns or sequences in coding or text formatting

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

    code syntax closing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.12
    ThroughAttribute
    -0.95
     beſte
    -0.87
    səhifə
    -0.86
    awtextra
    -0.85
    <unused52>
    -0.84
    <unused74>
    -0.84
    <unused43>
    -0.84
     témoig
    -0.84
    <unused14>
    -0.84
    POSITIVE LOGITS
     
    0.66
     the
    0.49
    '
    0.49
      
    0.48
       
    0.47
                    
    0.47
    /
    0.47
        
    0.47
    ...
    0.47
    1
    0.46
    Act Density 0.001%

    No Known Activations