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

    Neuronpedia

    INDEX
    Explanations

    explaining complex ideas in essays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     folks
    0.95
     পড়ে
    0.94
     পড়
    0.92
     দাঁড়
    0.88
     monto
    0.87
     oftentimes
    0.87
     يصير
    0.87
     customized
    0.86
     savor
    0.85
     kiddos
    0.84
    POSITIVE LOGITS
    Whilst
    1.15
     GCSE
    1.14
     (£
    1.13
     inbuilt
    1.09
     wastage
    1.09
     Whilst
    1.08
     timescales
    1.07
     adverts
    1.05
     organisers
    1.04
     spoilt
    1.04
    Act Density 0.156%

    No Known Activations