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

    Neuronpedia

    INDEX
    Explanations

    Code line numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zie
    -0.07
    spa
    -0.07
    ники
    -0.07
     multin
    -0.06
    '>{
    -0.06
    иту
    -0.06
    Delimiter
    -0.06
    astic
    -0.06
    243
    -0.06
    /ac
    -0.06
    POSITIVE LOGITS
    奖
    0.07
    "]))↵
    0.07
    -largest
    0.06
     державного
    0.06
     времени
    0.06
     ничего
    0.06
    BUG
    0.06
    �
    0.06
    出品
    0.06
    CTRL
    0.06
    Act Density 0.004%

    No Known Activations