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

    Neuronpedia

    INDEX
    Explanations

    qualities or situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ja
    0.36
    novu
    0.36
     D
    0.35
     "")
    0.35
     yg
    0.35
     them
    0.34
     primates
    0.34
     B
    0.34
     BC
    0.34
    '{
    0.34
    POSITIVE LOGITS
     کار
    0.47
     whatnot
    0.45
    ている
    0.44
     milieu
    0.42
     персона
    0.40
     conscience
    0.40
    ລັບ
    0.39
     عدم
    0.38
     cardiomyocyte
    0.38
    ແມ່ນ
    0.38
    Act Density 0.116%

    No Known Activations