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

    Neuronpedia

    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bans
    -0.07
    慈
    -0.07
    asp
    -0.07
    爱好
    -0.07
     elbow
    -0.07
    ');?></
    -0.07
    Hide
    -0.06
    放到
    -0.06
    除
    -0.06
    戒
    -0.06
    POSITIVE LOGITS
    쌘
    0.08
     quindi
    0.07
     בדיוק
    0.07
     güçlü
    0.07
     attributable
    0.07
    Enumerable
    0.07
    AnimationFrame
    0.07
    服务机构
    0.07
     굉장히
    0.07
     İ
    0.07
    Act Density 0.053%

    No Known Activations