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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ত্রী
    0.48
    ⟋
    0.48
    羵
    0.47
     easements
    0.46
    করিতে
    0.45
    志森
    0.44
    ভারতীয়
    0.43
     ẹ
    0.43
    ंखला
    0.42
    ”।
    0.42
    POSITIVE LOGITS
     )
    0.81
    ,)
    0.68
    ...)
    0.64
     )(
    0.63
    ())
    0.61
    %)
    0.60
     ))
    0.59
    1
    0.59
    !)
    0.59
    x
    0.58
    Act Density 0.088%

    No Known Activations