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

    Neuronpedia

    INDEX
    Explanations

    order for, Western Australia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    W
    0.92
     Semaphore
    0.83
    face
    0.83
    as
    0.82
    a
    0.82
     saath
    0.80
    M
    0.80
    б
    0.80
    ಹಿತ
    0.77
    o
    0.75
    POSITIVE LOGITS
    larını
    0.88
    ланды
    0.84
     khoảng
    0.83
    loot
    0.82
    rots
    0.78
    脍
    0.77
    ‌هایی
    0.76
     iced
    0.75
    мак
    0.75
    份额
    0.75
    Act Density 0.000%

    No Known Activations