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

    Neuronpedia

    INDEX
    Explanations

    government bills

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jehož
    -0.07
     ['-
    -0.07
    _fee
    -0.07
     queda
    -0.06
     ull
    -0.06
     यद
    -0.06
    aştır
    -0.06
    _prof
    -0.06
     прев
    -0.06
    Iterations
    -0.06
    POSITIVE LOGITS
    �
    0.07
     assert
    0.07
     Мас
    0.06
     Mus
    0.06
    Anchor
    0.06
     bottles
    0.06
    Enable
    0.06
     Rod
    0.06
    .define
    0.06
     scream
    0.06
    Act Density 0.001%

    No Known Activations