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

    Neuronpedia

    INDEX
    Explanations

    Masters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    纲
    -0.07
    윳
    -0.07
    executor
    -0.07
    宏
    -0.07
    определ
    -0.07
    御
    -0.07
    .gov
    -0.06
    promise
    -0.06
    basis
    -0.06
    大股东
    -0.06
    POSITIVE LOGITS
     infos
    0.07
     efficiently
    0.07
     pornography
    0.07
     programma
    0.07
    itably
    0.07
    (Y
    0.06
     subs
    0.06
    近乎
    0.06
     POLIT
    0.06
     goods
    0.06
    Act Density 0.065%

    No Known Activations