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

    Neuronpedia

    INDEX
    Explanations

    breakdown introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    시고
    0.43
    нинград
    0.43
    我可以
    0.42
     मसल
    0.42
    理由
    0.41
     लागि
    0.41
     टाइप्स
    0.40
     सूची
    0.40
     возмо
    0.40
    可能的
    0.39
    POSITIVE LOGITS
    ជីវ
    0.45
    [::-
    0.45
     accompanied
    0.42
     synonymous
    0.42
    witz
    0.40
    ogenesis
    0.40
     symbi
    0.40
     adjoint
    0.40
     bekannt
    0.39
     Details
    0.38
    Act Density 0.191%

    No Known Activations