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

    Neuronpedia

    INDEX
    Explanations

    bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    11
    -0.08
     CPF
    -0.07
    你
    -0.07
    701
    -0.06
    101
    -0.06
     Overview
    -0.06
     vida
    -0.06
     vine
    -0.06
    owl
    -0.06
     çalışan
    -0.06
    POSITIVE LOGITS
     bracket
    0.18
     Bracket
    0.17
    Bracket
    0.15
     brackets
    0.14
    ackets
    0.10
     Aber
    0.07
     مت
    0.07
    uet
    0.07
    рот
    0.07
     racket
    0.07
    Act Density 0.003%

    No Known Activations