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

    Neuronpedia

    INDEX
    Explanations

    distinct concepts in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     популација
    0.41
     이용하여
    0.40
     المسؤول
    0.40
     প্রাণ
    0.39
    ありが
    0.39
     klima
    0.39
     సమా
    0.38
    きの
    0.38
    システムの
    0.38
    流行的
    0.38
    POSITIVE LOGITS
     intend
    0.40
    бав
    0.39
     sart
    0.38
    tain
    0.37
     years
    0.36
     tendon
    0.36
    sir
    0.35
     disc
    0.35
     presumably
    0.35
     Leather
    0.35
    Act Density 0.000%

    No Known Activations