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

    Neuronpedia

    INDEX
    Explanations

    German language (or non-English)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dopo
    -0.07
    RSpec
    -0.07
     Üst
    -0.07
    _sections
    -0.07
     mezun
    -0.07
    ぞ
    -0.07
     začal
    -0.07
    _dirs
    -0.06
    kladní
    -0.06
     daß
    -0.06
    POSITIVE LOGITS
    ocolate
    0.07
     won
    0.06
    ัฐ
    0.06
    jsonwebtoken
    0.06
     Managed
    0.06
    inal
    0.06
    MU
    0.06
     subscript
    0.06
    teachers
    0.06
     winning
    0.06
    Act Density 0.010%

    No Known Activations