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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('/')
    -0.07
    ederation
    -0.06
     burn
    -0.06
     MainMenu
    -0.06
    {T
    -0.06
    _order
    -0.06
     воно
    -0.06
     inputStream
    -0.06
     libero
    -0.06
     Burning
    -0.06
    POSITIVE LOGITS
     researched
    0.08
     researching
    0.07
     entity
    0.07
    参与
    0.07
     centuries
    0.07
     Fuji
    0.06
    Credit
    0.06
     आदम
    0.06
     witch
    0.06
    每
    0.06
    Act Density 0.025%

    No Known Activations