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

    Neuronpedia

    INDEX
    Explanations

    than/that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     originates
    -0.07
     illustrations
    -0.06
     ".");↵
    -0.06
    itor
    -0.06
    INavigation
    -0.06
     Why
    -0.06
    ategic
    -0.06
     singing
    -0.06
     tee
    -0.06
     cur
    -0.06
    POSITIVE LOGITS
    圭圭
    0.07
     精
    0.06
    (pred
    0.06
    废
    0.06
     consoles
    0.06
    роиз
    0.06
    ：<
    0.06
    merchant
    0.06
    .documents
    0.06
    ":[{"
    0.06
    Act Density 0.016%

    No Known Activations