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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sex
    -0.06
    /display
    -0.06
     marty
    -0.06
    Alex
    -0.06
     narciss
    -0.06
     invo
    -0.06
     seemingly
    -0.06
     inventory
    -0.06
     refining
    -0.06
     facade
    -0.06
    POSITIVE LOGITS
     ServiceException
    0.07
    ức
    0.07
    .Automation
    0.07
    Diese
    0.06
     Iron
    0.06
     جستارهای
    0.06
    UnitOfWork
    0.06
     实
    0.06
    APPER
    0.06
    NewProp
    0.06
    Act Density 0.051%

    No Known Activations