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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bowman
    -0.07
     Erl
    -0.06
     Allan
    -0.06
     Karel
    -0.06
     Presbyterian
    -0.06
     Аль
    -0.06
    .docs
    -0.06
     ‪
    -0.06
     VIC
    -0.06
    hammer
    -0.06
    POSITIVE LOGITS
    (klass
    0.07
     }↵
    0.07
    perform
    0.07
     Locate
    0.07
     desire
    0.06
     melodies
    0.06
     Bars
    0.06
    &↵
    0.06
    $message
    0.06
    ITTLE
    0.06
    Act Density 0.001%

    No Known Activations