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

    Neuronpedia

    INDEX
    Explanations

    University of [place]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इंस्ट
    0.31
    它的
    0.31
    ÉS
    0.30
     दुष्प्रभावों
    0.30
    not
    0.30
    Τα
    0.30
    require
    0.30
     impedir
    0.30
    不
    0.29
     اعت
    0.29
    POSITIVE LOGITS
     Missouri
    0.36
    -
    0.33
    се
    0.32
    ance
    0.31
     Calgary
    0.31
     Southern
    0.31
     Charleston
    0.30
     Houston
    0.29
    ol
    0.29
     southern
    0.29
    Act Density 0.002%

    No Known Activations