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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     하
    -0.07
     validators
    -0.07
    орон
    -0.06
     lords
    -0.06
    177
    -0.06
     dug
    -0.06
     creative
    -0.06
     Heroes
    -0.06
     drivers
    -0.06
     Martin
    -0.06
    POSITIVE LOGITS
    anych
    0.06
     airy
    0.06
    orrh
    0.06
     آذرب
    0.06
     ут
    0.06
    NullException
    0.06
    دود
    0.06
     versatility
    0.06
     И
    0.06
     Stopwatch
    0.06
    Act Density 0.067%

    No Known Activations