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

    Neuronpedia

    INDEX
    Explanations

    campaign manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ار
    2.25
    på
    1.95
    र
    1.94
     определя
    1.91
    ла
    1.89
    có
    1.88
     уж
    1.85
    ंग
    1.83
    czny
    1.74
     asymmetry
    1.69
    POSITIVE LOGITS
    ्स
    2.13
    nent
    1.84
    ס
    1.84
    ви
    1.76
    ی
    1.76
    ד
    1.73
    ו
    1.67
    nels
    1.66
     불구하고
    1.65
    カイブ
    1.61
    Act Density 0.012%

    No Known Activations