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

    Neuronpedia

    INDEX
    Explanations

    business and service terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flavorful
    2.18
     lackluster
    2.14
     şi
    2.12
     এছাড়া
    1.89
     neighborhoods
    1.89
     meager
    1.89
     ছাড়া
    1.83
    Neighbors
    1.82
     phony
    1.82
     rumors
    1.77
    POSITIVE LOGITS
    Whilst
    2.68
     Whilst
    2.66
     whilst
    2.50
     enquiries
    2.50
     فى
    2.48
     £
    2.36
     recognises
    2.26
     recognised
    2.25
     bespoke
    2.19
     enquiry
    2.19
    Act Density 0.138%

    No Known Activations