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

    Neuronpedia

    INDEX
    Explanations

    common idiomatic phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Him
    0.42
     Thoughts
    0.37
     Tempt
    0.37
     Tr
    0.36
     Bottom
    0.36
     বৃত্তান্ত
    0.36
     Plan
    0.36
     Magic
    0.36
     Body
    0.35
     Pointer
    0.35
    POSITIVE LOGITS
     proverbial
    0.69
     पाकिस्तानी
    0.42
    ərbaycan
    0.42
    Н
    0.41
     또한
    0.41
     وكذلك
    0.41
     буквально
    0.38
     osim
    0.38
    ಗೋ
    0.38
    localVar
    0.38
    Act Density 0.041%

    No Known Activations