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

    Neuronpedia

    INDEX
    Explanations

    company URLs and cloud services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    佂
    0.48
     Elytres
    0.40
    lyPlugin
    0.39
    KEYDOWN
    0.38
    Articulation
    0.38
    Ɲ
    0.38
    薷
    0.38
    Ⅼ
    0.38
    ඪ
    0.38
    페이지
    0.38
    POSITIVE LOGITS
     nana
    0.43
     bü
    0.42
     grandmother
    0.42
     fitter
    0.41
     dazzling
    0.39
    astra
    0.39
     qualitative
    0.39
    куль
    0.39
     amante
    0.39
    Boe
    0.38
    Act Density 0.000%

    No Known Activations