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

    Neuronpedia

    INDEX
    Explanations

    kinds and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Something
    0.55
    Something
    0.51
    omer
    0.50
     Consumption
    0.47
     Whatever
    0.46
    IC
    0.45
     suatu
    0.44
     something
    0.44
     Someone
    0.44
     kommt
    0.43
    POSITIVE LOGITS
     kinds
    1.04
     types
    0.99
     things
    0.96
     aspects
    0.95
     categories
    0.94
     contexts
    0.90
    类型的
    0.89
    種類の
    0.87
     areas
    0.86
     countries
    0.81
    Act Density 0.329%

    No Known Activations