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

    Neuronpedia

    INDEX
    Explanations

    Laravel namespace imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.23
    ing
    0.94
    ية
    0.88
    ed
    0.87
    r
    0.83
    ים
    0.81
    ே
    0.81
    ou
    0.79
    ان
    0.77
     are
    0.77
    POSITIVE LOGITS
    𝙛
    0.68
    𝙜
    0.68
     exceptionnelle
    0.66
     ně
    0.65
     불구하고
    0.65
     oczywiście
    0.63
    屉
    0.62
    জ
    0.61
    וי
    0.61
     стране
    0.60
    Act Density 0.001%

    No Known Activations