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

    Neuronpedia

    INDEX
    Explanations

    artillery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    INES
    0.82
    А
    0.81
     efectiva
    0.76
    ი
    0.74
    am
    0.73
    ності
    0.73
    a
    0.72
    उंट
    0.69
    iendo
    0.68
    하는
    0.68
    POSITIVE LOGITS
     artillery
    0.77
    ర్లు
    0.68
     bağlı
    0.66
    Yea
    0.63
    ل
    0.63
    дям
    0.62
     mortars
    0.61
     Họ
    0.60
     premiums
    0.60
     tariffs
    0.57
    Act Density 0.001%

    No Known Activations