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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uran
    -0.07
     Roo
    -0.06
    essional
    -0.06
    :[],↵
    -0.06
     BBQ
    -0.06
     td
    -0.06
    =[];↵
    -0.06
    -san
    -0.06
    alian
    -0.06
    etim
    -0.06
    POSITIVE LOGITS
    .SetString
    0.07
    .setMessage
    0.07
     машин
    0.07
    _tol
    0.07
     Kop
    0.07
     mocks
    0.06
    �
    0.06
     vai
    0.06
    .SubItems
    0.06
    ٍ
    0.06
    Act Density 0.004%

    No Known Activations