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

    Neuronpedia

    INDEX
    Explanations

    code/email snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tense
    -0.07
     advanced
    -0.07
    ланд
    -0.07
     Nexus
    -0.06
    _parser
    -0.06
     drainage
    -0.06
     IDEA
    -0.06
     CRE
    -0.06
     Ahmed
    -0.06
    phoneNumber
    -0.06
    POSITIVE LOGITS
    )index
    0.07
    登
    0.07
    .Xtra
    0.06
    ियल
    0.06
     fals
    0.06
     residency
    0.06
    )):
↵
    0.06
    --[
    0.06
    กำล
    0.06
    imitives
    0.06
    Act Density 0.020%

    No Known Activations