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

    Neuronpedia

    INDEX
    Explanations

    is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     três
    1.44
     municípios
    1.41
     gerais
    1.38
     mètres
    1.34
     necessárias
    1.34
     funcionários
    1.31
     soorten
    1.30
     critérios
    1.30
     périodes
    1.29
     frères
    1.27
    POSITIVE LOGITS
    ल
    1.10
     that
    1.08
    便是
    1.05
     he
    1.03
     $(\
    1.02
    s
    0.99
     differentiating
    0.98
    '
    0.97
     attracting
    0.96
    ्स
    0.95
    Act Density 0.087%

    No Known Activations