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

    Neuronpedia

    INDEX
    Explanations

    embeddings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surround
    -0.08
    .chain
    -0.06
    τρι
    -0.06
     Correct
    -0.06
    遺
    -0.06
    \:
    -0.06
     declare
    -0.06
     desenv
    -0.06
    .serv
    -0.06
     Chron
    -0.06
    POSITIVE LOGITS
     фот
    0.07
    ités
    0.07
    -grade
    0.06
     fee
    0.06
     een
    0.06
     Colour
    0.06
    markt
    0.06
     extraordinarily
    0.06
     handing
    0.06
    _components
    0.06
    Act Density 0.015%

    No Known Activations