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

    Neuronpedia

    INDEX
    Explanations

    the word "brick" and words that can be names of teams

    oai_token-act-pair · gemini-2.0-flash

    buildings and construction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.44
     Anſ
    -1.44
     Jefus
    -1.41
     Theſe
    -1.41
     itſelf
    -1.38
    ſelf
    -1.38
     Reſ
    -1.38
     ainfi
    -1.37
     myſelf
    -1.33
     photolibrary
    -1.30
    POSITIVE LOGITS
     
    1.01
     (
    1.00
    .
    1.00
      
    0.96
    ,
    0.95
    ↵↵
    0.91
    ↵
    0.85
     <
    0.76
     in
    0.75
       
    0.73
    Act Density 0.482%

    No Known Activations