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

    Neuronpedia

    INDEX
    Explanations

    research and business

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Larry
    -0.07
    Larry
    -0.07
     John
    -0.07
     exceed
    -0.07
    itive
    -0.06
     slogan
    -0.06
     Drum
    -0.06
     invent
    -0.06
    ूट
    -0.06
     rather
    -0.06
    POSITIVE LOGITS
     nuestro
    0.07
     meditation
    0.07
    leshooting
    0.06
    (pipe
    0.06
    شاه
    0.06
     NoSuchElementException
    0.06
    ステム
    0.06
    .pipe
    0.06
    ादन
    0.06
     colossal
    0.06
    Act Density 0.747%

    No Known Activations