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

    Neuronpedia

    INDEX
    Explanations

    hidden

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fiction
    -0.06
     obed
    -0.06
     Insecta
    -0.06
     nen
    -0.06
     undone
    -0.06
     ве
    -0.06
     moda
    -0.06
    toHaveBeenCalledWith
    -0.06
    358
    -0.06
     Niger
    -0.06
    POSITIVE LOGITS
     cherished
    0.07
    Optional
    0.07
    omez
    0.07
    demo
    0.07
    .setSelection
    0.07
    ่าว
    0.07
     сиг
    0.06
     reserved
    0.06
    .yahoo
    0.06
    .previous
    0.06
    Act Density 0.001%

    No Known Activations