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

    Neuronpedia

    INDEX
    Explanations

    sector, actions, quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Industry
    0.41
     Darkness
    0.39
     fascism
    0.39
    Steam
    0.39
    Without
    0.38
    തിരെ
    0.38
    褸
    0.38
    Bald
    0.38
    Doesn
    0.38
     അഗ്
    0.38
    POSITIVE LOGITS
     lh
    0.41
     مند
    0.41
    الث
    0.40
    achi
    0.39
    \:
    0.39
    ổng
    0.39
     g
    0.39
    át
    0.39
     acontecimientos
    0.38
     г
    0.37
    Act Density 0.003%

    No Known Activations