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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hammer
    -0.07
     Bucks
    -0.07
    tığımız
    -0.07
     Defense
    -0.07
    cales
    -0.06
     ~/
    -0.06
    ();}↵
    -0.06
    }()↵↵
    -0.06
    成本
    -0.06
    大众
    -0.06
    POSITIVE LOGITS
     bribery
    0.07
    ADA
    0.07
     copies
    0.07
    蜩
    0.07
    ὰ
    0.06
    IFIC
    0.06
    .leave
    0.06
    iki
    0.06
    /or
    0.06
    河流域
    0.06
    Act Density 0.064%

    No Known Activations