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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prime
    -0.07
     Fundamental
    -0.07
     Carson
    -0.07
     Prevent
    -0.06
     inplace
    -0.06
     그리고
    -0.06
    NT
    -0.06
    (service
    -0.06
     tack
    -0.06
    (best
    -0.06
    POSITIVE LOGITS
    acak
    0.07
     gül
    0.07
    ička
    0.07
     userRepository
    0.07
    /signup
    0.06
    cedures
    0.06
    لیه
    0.06
     україн
    0.06
     recep
    0.06
     있음
    0.06
    Act Density 0.019%

    No Known Activations