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

    Neuronpedia

    INDEX
    Explanations

    seaborn as sns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     déliv
    0.37
     lésions
    0.35
    细胞
    0.34
     passwd
    0.34
     impairments
    0.34
     employability
    0.34
     cohom
    0.33
    зін
    0.33
     vésicules
    0.33
     appliquée
    0.33
    POSITIVE LOGITS
     prediksi
    0.40
     Jepang
    0.37
    ar
    0.37
     Indonesian
    0.37
     guna
    0.37
    untuk
    0.37
     Januari
    0.36
     tengah
    0.36
    ategori
    0.36
    ik
    0.36
    Act Density 0.001%

    No Known Activations