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

    Neuronpedia

    INDEX
    Explanations

    firmware updates and binding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.95
    ंनो
    0.74
    ने
    0.74
    1
    0.74
     resulta
    0.73
    0.73
    橥
    0.73
     fertil
    0.72
     logro
    0.72
     scrutin
    0.72
    POSITIVE LOGITS
    B
    1.05
    ↵
    0.88
     و
    0.88
    X
    0.81
    ib
    0.79
    conditioned
    0.78
    P
    0.77
    ‌های
    0.76
    og
    0.76
    ‌اند
    0.76
    Act Density 0.003%

    No Known Activations