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

    Neuronpedia

    INDEX
    Explanations

    道

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Atlas
    -0.10
     summit
    -0.08
     zoon
    -0.08
     enorme
    -0.08
    repositories
    -0.08
     bila
    -0.08
     bingo
    -0.08
     reunion
    -0.08
     начин
    -0.08
     الإنج
    -0.08
    POSITIVE LOGITS
     exploited
    0.09
     attacks
    0.09
    攻击
    0.08
     attaques
    0.08
     machine
    0.08
     demonstrations
    0.08
     exploiting
    0.08
     exploit
    0.08
     exploits
    0.08
     चिं
    0.08
    Act Density 0.002%

    No Known Activations