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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aniu
    -0.07
     Explosion
    -0.07
    侵略
    -0.07
    海盗
    -0.06
    缓解
    -0.06
     departed
    -0.06
     Mohammed
    -0.06
    edback
    -0.06
     actionPerformed
    -0.06
    bled
    -0.06
    POSITIVE LOGITS
     różnych
    0.09
     señor
    0.07
    (sim
    0.07
     lớp
    0.07
    -rate
    0.07
    自分が
    0.07
     główne
    0.07
    missão
    0.07
    ➨
    0.07
    쫘
    0.07
    Act Density 0.017%

    No Known Activations