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

    Neuronpedia

    INDEX
    Explanations

    squid, calamari, prawns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ン
    0.98
    न
    0.96
    ن
    0.91
    ت
    0.87
    ਰ
    0.82
    ز
    0.81
    on
    0.78
    ३
    0.77
    وک
    0.77
    ail
    0.76
    POSITIVE LOGITS
    ará
    1.00
     as
    0.97
    ına
    0.95
     aquela
    0.91
    ında
    0.90
     erős
    0.86
    தான்
    0.83
    arı
    0.82
    ى
    0.80
     acesta
    0.78
    Act Density 0.000%

    No Known Activations