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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blessed
    -0.07
    What
    -0.07
    파
    -0.07
     indexOf
    -0.07
    上の
    -0.06
    กระบ
    -0.06
     Lucky
    -0.06
     utrecht
    -0.06
    想像
    -0.06
    Computed
    -0.06
    POSITIVE LOGITS
    ILLISE
    0.07
    念头
    0.07
     cron
    0.07
     viewController
    0.07
    命令
    0.07
     knitting
    0.07
     Vim
    0.06
     ―
    0.06
    夜晚
    0.06
    💈
    0.06
    Act Density 0.004%

    No Known Activations