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

    Neuronpedia

    INDEX
    Explanations

    say "s" word

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    梯
    -0.08
    رص
    -0.08
     Get
    -0.08
    Visibility
    -0.07
    ified
    -0.07
    strain
    -0.07
     recognition
    -0.07
     dai
    -0.07
     revelation
    -0.07
    主題
    -0.07
    POSITIVE LOGITS
     defects
    0.08
    讧
    0.08
     יצירת
    0.08
     defect
    0.08
     fds
    0.08
    没法
    0.07
     Fault
    0.07
     disabilities
    0.07
     injured
    0.07
     (^)(
    0.07
    Act Density 0.009%

    No Known Activations