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

    Neuronpedia

    INDEX
    Explanations

    URLs and code repositories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     шт
    -0.08
    quantity
    -0.08
    ‡
    -0.08
    istorical
    -0.08
    ాప
    -0.08
     "<<
    -0.08
    Covid
    -0.08
     Lol
    -0.08
     distorted
    -0.08
    �
    -0.07
    POSITIVE LOGITS
     aston
    0.09
     SQL
    0.08
    链接
    0.08
     documentação
    0.08
    o
    0.07
     composer
    0.07
     debated
    0.07
     revis
    0.07
     buch
    0.07
     அல
    0.07
    Act Density 0.009%

    No Known Activations