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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NS
    -0.08
     Palest
    -0.08
    isd
    -0.07
    sh
    -0.07
     odense
    -0.07
    ulling
    -0.07
    (des
    -0.07
    .onload
    -0.07
    etxt
    -0.07
    %=
    -0.07
    POSITIVE LOGITS
     שלו
    0.07
    �
    0.07
    enderror
    0.07
     "\",
    0.07
     совершен
    0.07
    حد
    0.07
     cand
    0.06
     chose
    0.06
     chù
    0.06
    🧲
    0.06
    Act Density 0.045%

    No Known Activations