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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    народ
    -0.08
     schauen
    -0.08
    ехать
    -0.08
    problem
    -0.08
    _problem
    -0.07
    Goal
    -0.07
    ଶ
    -0.07
    stdlib
    -0.07
     maneiras
    -0.07
    _targets
    -0.07
    POSITIVE LOGITS
    详细
    0.11
     glossary
    0.11
     Detailed
    0.10
     detailed
    0.10
     Tables
    0.09
     Gloss
    0.09
     technical
    0.09
     Appendix
    0.09
    相关
    0.09
     табли
    0.09
    Act Density 0.006%

    No Known Activations