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

    Neuronpedia

    INDEX
    Explanations

    causes and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     svou
    0.46
     avendo
    0.46
     свої
    0.44
     svojim
    0.41
     gebruiken
    0.38
     savo
    0.38
     Ако
    0.38
     possède
    0.37
     사용하는
    0.37
     possèdent
    0.37
    POSITIVE LOGITS
     peningkatan
    0.66
     a
    0.62
     increased
    0.60
     an
    0.55
     more
    0.55
     changes
    0.53
     increase
    0.50
     unprecedented
    0.50
     aumento
    0.49
     disillusion
    0.49
    Act Density 0.244%

    No Known Activations