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

    Neuronpedia

    INDEX
    Explanations

    Technical/Informative writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الب
    -0.06
     Bite
    -0.06
     brawl
    -0.06
     Alison
    -0.06
    접
    -0.06
     Unt
    -0.06
     spite
    -0.06
    CELL
    -0.06
    OfFile
    -0.06
    AINER
    -0.06
    POSITIVE LOGITS
    Charlotte
    0.06
     RPG
    0.06
    .getFullYear
    0.06
    ！！
    0.06
     Pompeo
    0.06
    fat
    0.06
    .In
    0.06
    Passwords
    0.06
     kanı
    0.06
    廣
    0.06
    Act Density 0.000%

    No Known Activations