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

    Neuronpedia

    INDEX
    Explanations

    countries and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naprawdę
    0.38
     ወይም
    0.37
     trover
    0.33
     konuştu
    0.33
    <unused395>
    0.33
     financière
    0.32
    というのは
    0.32
    滪
    0.32
     ಸಿನಿ
    0.32
     davvero
    0.31
    POSITIVE LOGITS
     Indonesia
    0.44
     Netherlands
    0.43
     Philippines
    0.40
     Australia
    0.39
    .
    0.38
     Sweden
    0.38
     UAE
    0.38
     University
    0.38
     Tanzania
    0.37
     Instit
    0.37
    Act Density 0.026%

    No Known Activations