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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [count
    -0.07
    archy
    -0.07
     radians
    -0.06
    Lets
    -0.06
    히
    -0.06
    .Car
    -0.06
    171
    -0.06
    ۱
    -0.06
     ARC
    -0.06
    џЭ
    -0.06
    POSITIVE LOGITS
    ักร
    0.06
     Mushroom
    0.06
     vùng
    0.06
    рім
    0.06
     наприклад
    0.06
    adaptiveStyles
    0.06
     عفش
    0.06
     Shea
    0.06
     zengin
    0.06
    ']?>
    0.06
    Act Density 0.030%

    No Known Activations