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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beneficiary
    -0.07
     Rh
    -0.07
    rippling
    -0.07
    .MenuItem
    -0.07
     selectors
    -0.07
    roker
    -0.07
     elephant
    -0.07
    -0.07
     underrated
    -0.07
    
    -0.07
    POSITIVE LOGITS
     tcp
    0.06
     cena
    0.05
     výrob
    0.05
    methodPointerType
    0.05
     ratings
    0.05
     NDEBUG
    0.05
     науч
    0.05
     Reyn
    0.05
    .findAll
    0.05
     Caval
    0.05
    Act Density 0.007%

    No Known Activations