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

    Neuronpedia

    INDEX
    Explanations

    capital

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    憙
    -0.08
    worked
    -0.07
    utowired
    -0.07
    otal
    -0.07
    选出
    -0.07
     curated
    -0.07
    煦
    -0.07
    gem
    -0.07
    董事
    -0.07
     hated
    -0.07
    POSITIVE LOGITS
    �
    0.08
    Case
    0.08
     방
    0.07
    둔
    0.07
     civic
    0.07
    .Parser
    0.07
    ポン
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    ...
    0.07
     الوق
    0.07
    Act Density 0.006%

    No Known Activations