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

    Neuronpedia

    INDEX
    Explanations

    segments of text containing repeated patterns or structures

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

    code, math, and text data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.87
     faſt
    -0.85
    <unused14>
    -0.82
     $_"
    -0.82
    <unused16>
    -0.82
    <unused8>
    -0.82
    <unused52>
    -0.82
    <unused68>
    -0.82
    <unused51>
    -0.82
    [@BOS@]
    -0.82
    POSITIVE LOGITS
         
    1.48
          
    0.99
        
    0.95
           
    0.89
                        
    0.89
                 
    0.88
                         
    0.87
             
    0.86
    0.76
                     
    0.75
    Act Density 0.042%

    No Known Activations