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

    Neuronpedia

    INDEX
    Explanations

    summary:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nymphs
    0.41
    भाष
    0.40
     Maß
    0.39
     mammals
    0.39
     isoforms
    0.39
     süt
    0.37
     Tháng
    0.36
     orifices
    0.36
     mesothelioma
    0.36
     cookware
    0.35
    POSITIVE LOGITS
    rown
    0.45
    to
    0.43
    elt
    0.42
    બ
    0.42
    called
    0.41
    back
    0.41
    Abdul
    0.41
    last
    0.39
    lerden
    0.38
    ítě
    0.38
    Act Density 0.032%

    No Known Activations