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

    Neuronpedia

    INDEX
    Explanations

    Attorney

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stat
    -0.07
    力
    -0.07
    知识产权
    -0.07
    .files
    -0.06
    /select
    -0.06
     evaluation
    -0.06
    润滑
    -0.06
     girlfriends
    -0.06
    者が
    -0.06
     exploring
    -0.06
    POSITIVE LOGITS
    습니까
    0.07
     NAND
    0.07
     Ав
    0.06
    ᅯ
    0.06
    MOOTH
    0.06
    Grey
    0.06
     הנוכחי
    0.06
     countert
    0.06
     админист
    0.06
     CO
    0.06
    Act Density 0.001%

    No Known Activations