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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wallets
    -0.06
     tác
    -0.06
     Chrome
    -0.06
    783
    -0.06
    Moves
    -0.06
     Matter
    -0.06
     dresses
    -0.06
    典
    -0.06
     paragraphs
    -0.06
    lv
    -0.06
    POSITIVE LOGITS
    (?:
    0.07
    ÜR
    0.07
     AIR
    0.06
     otra
    0.06
    .ndim
    0.06
    (inner
    0.06
     tr
    0.06
     '=
    0.06
     як
    0.06
     verdienen
    0.06
    Act Density 0.057%

    No Known Activations