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

    Neuronpedia

    INDEX
    Explanations

    expressing reluctance or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বিষয়ে
    0.90
     অবা
    0.86
     সেগুলি
    0.85
     violation
    0.81
     pretty
    0.81
     এছাড়া
    0.81
     violates
    0.80
     minimizes
    0.79
     minimize
    0.78
     Pretty
    0.78
    POSITIVE LOGITS
     dodgy
    1.07
     classed
    1.01
     reckons
    0.99
     Whilst
    0.96
     footballer
    0.96
     bloke
    0.94
     rubbish
    0.92
     lorry
    0.92
    Whilst
    0.92
     inbuilt
    0.90
    Act Density 0.024%

    No Known Activations