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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Replies
    -0.08
    相关的
    -0.07
    规划建设
    -0.07
     Company
    -0.07
    麻木
    -0.07
     brave
    -0.07
    .ReadAsStringAsync
    -0.07
     Interesting
    -0.07
    的例子
    -0.07
    打磨
    -0.07
    POSITIVE LOGITS
    POR
    0.08
     Crit
    0.08
     glitter
    0.08
     iniciar
    0.07
     gid
    0.07
     STEP
    0.07
     specifier
    0.07
     غال
    0.07
    isper
    0.07
    Didn
    0.07
    Act Density 0.011%

    No Known Activations