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

    Neuronpedia

    INDEX
    Explanations

    say "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cılar
    -0.07
    措
    -0.07
    σου
    -0.07
     remedies
    -0.07
     sırada
    -0.06
     painting
    -0.06
     sitting
    -0.06
     постанов
    -0.06
     aplicación
    -0.06
     jestli
    -0.06
    POSITIVE LOGITS
    ,obj
    0.06
     Jes
    0.06
     optimize
    0.06
     IReadOnly
    0.06
    _operations
    0.06
     Ipsum
    0.06
     daring
    0.06
    _FAILED
    0.06
     Reef
    0.06
    /auth
    0.06
    Act Density 0.012%

    No Known Activations