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

    Neuronpedia

    INDEX
    Explanations

    solving problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    রাদ
    0.39
     officielle
    0.38
    缃
    0.37
     නිර්
    0.37
     explanations
    0.36
    过程中
    0.36
     explanation
    0.35
     ব্যবহৃত
    0.35
     Veranstaltungen
    0.35
     Gerais
    0.35
    POSITIVE LOGITS
     problems
    2.05
     problem
    2.02
     problema
    1.98
     проблему
    1.98
     problème
    1.92
     проблема
    1.89
     problèmes
    1.88
     문제를
    1.88
     problemas
    1.87
     проблемы
    1.86
    Act Density 0.035%

    No Known Activations