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

    Neuronpedia

    INDEX
    Explanations

    about something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पोप
    0.41
    邢
    0.41
     terület
    0.38
    দ্বিতীয়
    0.37
    城区
    0.37
     تعالى
    0.35
     ngựa
    0.35
    izoph
    0.35
    र्‍या
    0.35
     Bereich
    0.35
    POSITIVE LOGITS
     arras
    0.41
    atin
    0.39
    mmas
    0.36
     hooks
    0.36
    genstein
    0.36
     dram
    0.35
     J
    0.35
    ላይ
    0.35
     Herzen
    0.35
    نید
    0.34
    Act Density 0.003%

    No Known Activations