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

    Neuronpedia

    INDEX
    Explanations

    policy documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    --
    -0.08
     plaintext
    -0.08
    plaintext
    -0.08
    -existing
    -0.08
     नीचे
    -0.08
    |
    -0.07
     adjectives
    -0.07
     -
    -0.07
     chronological
    -0.07
    Thus
    -0.07
    POSITIVE LOGITS
     dismant
    0.11
     പദ്ധത
    0.10
     initiatives
    0.10
     확대
    0.09
     hiring
    0.09
     مكافحة
    0.09
     xây
    0.08
     nghiên
    0.08
     개발
    0.08
    Blockchain
    0.08
    Act Density 0.048%

    No Known Activations