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

    Neuronpedia

    INDEX
    Explanations

    Alexandre Dumas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    0.84
    %
    0.82
    л
    0.81
    م
    0.81
    м
    0.80
    ب
    0.79
    ক
    0.78
    struktur
    0.76
    ?
    0.72
    :
    0.71
    POSITIVE LOGITS
    िन
    0.66
    ំន
    0.64
     ingresos
    0.64
     giảm
    0.60
     подс
    0.60
     disminución
    0.59
     replenish
    0.59
    ري
    0.57
     "|
    0.57
     inflate
    0.57
    Act Density 0.003%

    No Known Activations