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

    Neuronpedia

    INDEX
    Explanations

    div

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     workshop
    -0.08
    praak
    -0.07
    ורך
    -0.07
     conductivity
    -0.06
     JL
    -0.06
    ☞
    -0.06
    과
    -0.06
    coder
    -0.06
    /***/
    -0.06
    Animation
    -0.06
    POSITIVE LOGITS
    百分之
    0.07
    矢
    0.07
    ⽀
    0.07
     четыре
    0.07
    支付
    0.07
     redu
    0.07
    萁
    0.06
     btc
    0.06
     desde
    0.06
    percent
    0.06
    Act Density 0.000%

    No Known Activations