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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بوت
    -0.09
     ulcer
    -0.08
    甗
    -0.08
    ursively
    -0.07
    BOSE
    -0.07
     Furious
    -0.07
     osób
    -0.07
     chop
    -0.06
    oucher
    -0.06
     Refriger
    -0.06
    POSITIVE LOGITS
    CTL
    0.07
    大盘
    0.07
    ].↵
    0.07
     '!
    0.07
    你是
    0.07
    ('.')↵
    0.07
    avelength
    0.06
     $↵
    0.06
      
↵
    0.06
    about
    0.06
    Act Density 0.003%

    No Known Activations