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

    Neuronpedia

    INDEX
    Explanations

    exclamation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     получили
    -0.08
    ONT
    -0.08
     دل
    -0.08
     انگلی
    -0.08
     শেষে
    -0.07
    (context
    -0.07
     குறித்து
    -0.07
    servers
    -0.07
     оф
    -0.07
     gồm
    -0.07
    POSITIVE LOGITS
     আও
    0.08
    unay
    0.08
     pastime
    0.08
     pairing
    0.08
     heroine
    0.07
     방
    0.07
     Tup
    0.07
     plastik
    0.07
     playoff
    0.07
     матч
    0.07
    Act Density 0.018%

    No Known Activations