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

    Neuronpedia

    INDEX
    Explanations

    code, math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (extension
    -0.07
    centre
    -0.07
    mouseover
    -0.07
    arsity
    -0.06
    rolls
    -0.06
    -eyed
    -0.06
    تي
    -0.06
    .menu
    -0.06
     sections
    -0.06
     Analyzer
    -0.06
    POSITIVE LOGITS
     accomplished
    0.07
     dating
    0.06
    ู
    0.06
     arrived
    0.06
    .fail
    0.06
    ufficient
    0.06
                  
↵
    0.06
               
↵
    0.06
     clase
    0.06
    erte
    0.06
    Act Density 0.011%

    No Known Activations