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

    Neuronpedia

    INDEX
    Explanations

    need or want help/ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meld
    0.41
     Cana
    0.38
    さは
    0.38
    澱
    0.37
    ायक
    0.37
     Saud
    0.37
    えられる
    0.37
     co
    0.36
     Fin
    0.36
     all
    0.36
    POSITIVE LOGITS
     ወቅ
    0.44
    বত
    0.42
     ilç
    0.42
     месяца
    0.41
     âge
    0.40
     shew
    0.40
     genç
    0.39
     যাহ
    0.39
    နှစ်
    0.39
     încep
    0.39
    Act Density 0.018%

    No Known Activations