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

    Neuronpedia

    INDEX
    Explanations

    Table of contents/agenda

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trekken
    -0.10
     accepter
    -0.08
     observa
    -0.08
    uttu
    -0.08
     recogn
    -0.08
     CHP
    -0.07
     recruits
    -0.07
     bettor
    -0.07
    岭
    -0.07
    ongodb
    -0.07
    POSITIVE LOGITS
     Topics
    0.12
     topics
    0.12
    topics
    0.11
    .sections
    0.10
    /topics
    0.10
    _sections
    0.10
    Topics
    0.10
    _topic
    0.09
    本文
    0.09
     tóp
    0.09
    Act Density 0.069%

    No Known Activations