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

    Neuronpedia

    INDEX
    Explanations

    définir, découverte, décomposer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    щенко
    0.41
    iction
    0.41
    indicator
    0.41
     epidemiological
    0.38
    ates
    0.38
    ވި
    0.38
    ictions
    0.38
     contribut
    0.38
     devaluation
    0.38
    вами
    0.37
    POSITIVE LOGITS
    duire
    0.48
    duit
    0.45
    完毕
    0.40
    du
    0.40
    duced
    0.39
    घु
    0.39
     組
    0.39
    埃及
    0.39
     পার্শ্ব
    0.38
     terminating
    0.38
    Act Density 0.003%

    No Known Activations