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

    Neuronpedia

    INDEX
    Explanations

    profanity

    oai_token-act-pair · gemini-2.0-flash

    Swearing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
      
    -1.07
     
    -0.95
     to
    -0.88
     _
    -0.86
     {
    -0.83
     on
    -0.81
     the
    -0.81
     a
    -0.80
     (
    -0.80
    ↵
    -0.80
    POSITIVE LOGITS
     Efq
    1.77
     itſelf
    1.70
     ―――――
    1.66
     ་་
    1.65
     myſelf
    1.60
     Majefty
    1.56
     Jefus
    1.52
     photolibrary
    1.50
     iſt
    1.42
     Houſe
    1.41
    Act Density 2.755%

    No Known Activations