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

    Neuronpedia

    INDEX
    Explanations

    stress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orbits
    -0.08
    odí
    -0.07
    inition
    -0.07
    enheim
    -0.06
     joint
    -0.06
     Lieutenant
    -0.06
    hong
    -0.06
     edge
    -0.06
     weg
    -0.06
    ую
    -0.06
    POSITIVE LOGITS
     investigates
    0.07
    adds
    0.06
    рис
    0.06
     Akron
    0.06
    Stock
    0.06
     soils
    0.06
    styles
    0.06
     athletics
    0.06
    ‐‐
    0.06
     tallest
    0.06
    Act Density 0.004%

    No Known Activations