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

    Neuronpedia

    INDEX
    Explanations

    science of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人文
    0.38
    tried
    0.37
     सबक
    0.37
    ேத
    0.36
    神
    0.36
    Centers
    0.35
    ूनी
    0.34
    ರಿನ
    0.34
    ethical
    0.34
    World
    0.34
    POSITIVE LOGITS
     لماذا
    0.47
     lactation
    0.46
     وګ
    0.44
     szükség
    0.41
     заболеваний
    0.40
     why
    0.40
     bagaimana
    0.40
     undergraduates
    0.40
     tumours
    0.40
     coalgebras
    0.39
    Act Density 0.012%

    No Known Activations