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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    커
    -0.06
    -established
    -0.06
     V
    -0.06
    otos
    -0.06
     "(
    -0.06
     É
    -0.06
     clearly
    -0.06
     К
    -0.06
    _rel
    -0.06
    iverse
    -0.06
    POSITIVE LOGITS
     السي
    0.07
     reordered
    0.06
     svat
    0.06
     роз
    0.06
     προσ
    0.06
     Lans
    0.06
    .destroyAllWindows
    0.06
     bal
    0.06
    innamon
    0.06
     cinnamon
    0.06
    Act Density 0.003%

    No Known Activations