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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arena
    -0.07
     здесь
    -0.06
    (stypy
    -0.06
    coles
    -0.06
    nicas
    -0.06
    kân
    -0.06
    _Normal
    -0.06
     inicio
    -0.06
    tol
    -0.06
    PostalCodes
    -0.06
    POSITIVE LOGITS
     rods
    0.07
    سیون
    0.07
    izzy
    0.06
     carts
    0.06
    singular
    0.06
     webdriver
    0.06
     ENGINE
    0.06
    热
    0.06
    熱
    0.06
     zem
    0.06
    Act Density 0.001%

    No Known Activations