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

    Neuronpedia

    INDEX
    Explanations

    forum questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    caps
    -0.08
     Highly
    -0.07
     anlam
    -0.07
     synonym
    -0.07
     nomination
    -0.07
    存在
    -0.06
    บก
    -0.06
    �
    -0.06
     wl
    -0.06
    声音
    -0.06
    POSITIVE LOGITS
     قرارد
    0.07
     GCC
    0.07
     jackpot
    0.06
     utilizing
    0.06
     dood
    0.06
    xF
    0.06
     ------>
    0.06
    //------------------------------------------------------------------------------↵↵
    0.06
    caffold
    0.06
     togg
    0.06
    Act Density 0.034%

    No Known Activations