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

    Neuronpedia

    INDEX
    Explanations

    heart health and disease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.02
    se
    1.01
    haltung
    1.01
    дой
    0.95
    दैन
    0.94
    נ
    0.93
    UARY
    0.93
    ндә
    0.93
    ف
    0.90
    든지
    0.89
    POSITIVE LOGITS
     petits
    0.93
     χρήση
    0.92
     Shades
    0.91
     élarg
    0.89
     mạnh
    0.88
     ayrıca
    0.87
    韜
    0.86
    та
    0.86
     lần
    0.83
     γεν
    0.83
    Act Density 0.003%

    No Known Activations