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

    Neuronpedia

    INDEX
    Explanations

    science, technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Zip
    -0.07
    =size
    -0.06
    (static
    -0.06
     ست
    -0.06
    ি
    -0.06
    \Factories
    -0.06
    amber
    -0.06
     trivia
    -0.06
    forEach
    -0.06
     např
    -0.06
    POSITIVE LOGITS
    \v
    0.08
    .)
    0.07
     desarroll
    0.06
    Register
    0.06
    ニニ
    0.06
    바이
    0.06
        ↵    ↵    ↵    ↵
    0.06
    .ignore
    0.06
     heals
    0.06
     scaled
    0.06
    Act Density 0.278%

    No Known Activations