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

    Neuronpedia

    INDEX
    Explanations

    extract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Card
    -0.06
    pty
    -0.06
     TD
    -0.06
    니
    -0.06
     wei
    -0.06
     Medium
    -0.06
     II
    -0.06
     Wanna
    -0.06
    zi
    -0.05
     Ade
    -0.05
    POSITIVE LOGITS
     Lafayette
    0.07
     некоторые
    0.07
     fscanf
    0.07
    Seeder
    0.07
     bouts
    0.07
    (:,:,
    0.07
    _launcher
    0.07
    _PRODUCTS
    0.07
     submerged
    0.07
    ijkl
    0.06
    Act Density 0.003%

    No Known Activations