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

    Neuronpedia

    INDEX
    Explanations

    audio/video encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Row
    -0.08
     والمح
    -0.08
    (Row
    -0.08
    Reporter
    -0.08
     Absolute
    -0.08
     ремонта
    -0.08
     ফর
    -0.08
     troll
    -0.08
     magician
    -0.08
     moch
    -0.07
    POSITIVE LOGITS
     áudio
    0.09
     спут
    0.08
     provenant
    0.08
    音
    0.08
     separate
    0.08
    附
    0.07
    φων
    0.07
    与此同时
    0.07
     bubbling
    0.07
     bary
    0.07
    Act Density 0.007%

    No Known Activations