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

    Neuronpedia

    INDEX
    Explanations

    historical figures or names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tunisie
    0.47
    পাকিস্তানের
    0.41
    銠
    0.40
    Jessica
    0.40
    鈮
    0.39
     Bous
    0.39
    Deborah
    0.38
    lib
    0.38
    𐰤
    0.38
    흔
    0.37
    POSITIVE LOGITS
     Napoleon
    0.69
     very
    0.58
     ladies
    0.58
     Fitzsimmons
    0.54
     Lord
    0.53
     nap
    0.53
     charge
    0.50
     lady
    0.50
     person
    0.48
     Fitz
    0.48
    Act Density 0.000%

    No Known Activations