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

    Neuronpedia

    INDEX
    Explanations

    let the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दिलचस्प
    0.93
     (!
    0.89
    !
    0.88
    YOUR
    0.87
    WHAT
    0.85
    !:
    0.85
    !"
    0.84
     YOUR
    0.84
    ?!?
    0.84
    OK
    0.83
    POSITIVE LOGITS
     upto
    1.58
     sarees
    1.40
     saree
    1.39
     atleast
    1.35
     equipments
    1.34
     irrespective
    1.32
     می‌باشد
    1.31
     inorder
    1.23
     inbuilt
    1.22
     sufferings
    1.18
    Act Density 0.002%

    No Known Activations