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

    Neuronpedia

    INDEX
    Explanations

    、

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Troubles
    -0.09
     troubleshoot
    -0.09
     dépannage
    -0.09
     Martin
    -0.09
     WAN
    -0.08
     departments
    -0.08
    Trou
    -0.08
     Och
    -0.08
     Hr
    -0.07
     chalk
    -0.07
    POSITIVE LOGITS
    股票
    0.11
     股票
    0.11
    portfolio
    0.10
    策略
    0.10
    episode
    0.10
     saham
    0.10
    证券
    0.10
     prescriptions
    0.10
     Portfolio
    0.09
     portfolio
    0.09
    Act Density 0.008%

    No Known Activations