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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     otevř
    -0.06
    Private
    -0.06
    ろ
    -0.05
    prech
    -0.05
    988
    -0.05
     ruku
    -0.05
    ified
    -0.05
     wollen
    -0.05
    Volumes
    -0.05
    oka
    -0.05
    POSITIVE LOGITS
    \$
    0.08
    _MISS
    0.07
     lsp
    0.07
    Us
    0.07
     she
    0.06
    (mock
    0.06
    ItemList
    0.06
    Toronto
    0.06
     Tow
    0.06
    (pair
    0.06
    Act Density 0.050%

    No Known Activations