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

    Neuronpedia

    INDEX
    Explanations

    tendencies of nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     đã
    -1.13
    лан
    -0.94
    えば
    -0.93
     jsem
    -0.91
     aktuell
    -0.90
     [{
    -0.89
    gary
    -0.88
    ebly
    -0.88
     huidige
    -0.87
    owulf
    -0.83
    POSITIVE LOGITS
     tend
    1.95
     don
    1.83
     tends
    1.81
     can
    1.54
     rarely
    1.48
     generally
    1.43
     notoriously
    1.42
     usually
    1.39
     seldom
    1.29
     Tend
    1.27
    Act Density 0.102%

    No Known Activations