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

    Neuronpedia

    INDEX
    Explanations

    verified and approved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     specifications
    0.43
     раху
    0.41
     питання
    0.39
     المواد
    0.39
     bienes
    0.39
     cũ
    0.38
    ソ
    0.38
    Specifications
    0.38
     দেবযানীর
    0.38
     Specifications
    0.38
    POSITIVE LOGITS
     expert
    0.61
     vetted
    0.55
     certified
    0.54
     verified
    0.54
     экспер
    0.51
    verified
    0.51
     Expert
    0.50
     approved
    0.50
    expert
    0.48
     skilled
    0.48
    Act Density 0.000%

    No Known Activations