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

    Neuronpedia

    INDEX
    Explanations

    doesn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Constitutional
    -0.07
    _formats
    -0.07
     Shared
    -0.07
    Database
    -0.06
    _DATABASE
    -0.06
     boiling
    -0.06
     governments
    -0.06
    QS
    -0.06
    QM
    -0.06
    185
    -0.06
    POSITIVE LOGITS
     sami
    0.07
     praw
    0.07
    徽
    0.06
     prav
    0.06
     現
    0.06
     autre
    0.06
    린이
    0.06
     relied
    0.06
     Nẵng
    0.06
     privile
    0.06
    Act Density 0.027%

    No Known Activations