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

    Neuronpedia

    INDEX
    Explanations

    academic manuscripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فناوری
    -0.09
     Individuals
    -0.08
     Sources
    -0.08
     Names
    -0.08
     caminar
    -0.08
     događ
    -0.08
     منابع
    -0.08
     negligible
    -0.08
     Ereign
    -0.07
     Kreuz
    -0.07
    POSITIVE LOGITS
    投稿
    0.11
     জম
    0.09
    审核
    0.09
    Ready
    0.09
     投稿
    0.09
    Submitting
    0.09
    submitted
    0.09
    Rejected
    0.09
    版
    0.09
     제출
    0.09
    Act Density 0.015%

    No Known Activations