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

    Neuronpedia

    INDEX
    Explanations

    something more unexpected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Complete
    0.43
    Complete
    0.39
    Kevin
    0.38
     doh
    0.38
     complete
    0.37
     Kevin
    0.37
     cleared
    0.37
     Proven
    0.36
     clever
    0.35
     contested
    0.35
    POSITIVE LOGITS
     siding
    0.41
    instrList
    0.41
    下げ
    0.40
     saree
    0.40
     ')[
    0.39
     mundur
    0.39
     sidang
    0.39
     Michal
    0.38
     भाजी
    0.38
    риф
    0.38
    Act Density 0.001%

    No Known Activations