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

    Neuronpedia

    INDEX
    Explanations

    logical inference and deduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     خدمات
    0.57
    ستخدم
    0.55
    服务
    0.50
     grabado
    0.50
    ម៉
    0.50
     servici
    0.49
     استخدم
    0.48
    服務
    0.48
    خدم
    0.47
     embarking
    0.47
    POSITIVE LOGITS
     propositional
    0.82
     inferences
    0.80
     statements
    0.73
     predicate
    0.70
     falsehood
    0.70
     Proposition
    0.69
     logically
    0.68
     inference
    0.68
     कथन
    0.68
     truth
    0.66
    Act Density 0.144%

    No Known Activations