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

    Neuronpedia

    INDEX
    Explanations

    titles, occurrences, and financial metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kleines
    0.41
     الكم
    0.39
     Königs
    0.38
     fores
    0.37
     raat
    0.36
     foes
    0.36
     irr
    0.36
     dha
    0.36
     ragione
    0.36
     ara
    0.36
    POSITIVE LOGITS
    oyloxy
    0.40
     Burt
    0.39
    техни
    0.38
     Уда
    0.38
    टू
    0.38
    hexyl
    0.37
    blog
    0.37
    brush
    0.36
     жаса
    0.36
     делу
    0.36
    Act Density 0.000%

    No Known Activations