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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     반드시
    0.34
     contamin
    0.33
     innumerable
    0.30
     extravaganza
    0.29
     guarant
    0.28
    𝐩
    0.28
     tokens
    0.28
     violators
    0.28
    Sched
    0.28
    讨
    0.28
    POSITIVE LOGITS
     Are
    0.61
    Are
    0.59
    Does
    0.55
     Does
    0.55
     Could
    0.55
    Would
    0.54
     Would
    0.54
    Could
    0.54
     Did
    0.52
     Is
    0.51
    Act Density 0.031%

    No Known Activations