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

    Neuronpedia

    INDEX
    Explanations

    worldwide business, leader, or average

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    های
    2.78
    нің
    2.38
    هایی
    2.31
    nál
    2.20
    тся
    2.06
    nél
    2.06
    ным
    2.05
    ról
    1.97
    Já
    1.94
     cardí
    1.92
    POSITIVE LOGITS
    c
    1.88
    ];
    1.85
    り
    1.85
     Directories
    1.74
    CTION
    1.73
    ະຍ
    1.73
    ees
    1.72
    flakes
    1.70
    ];//
    1.68
    酯
    1.66
    Act Density 0.002%

    No Known Activations