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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.04
    r
    0.81
    an
    0.79
    у
    0.79
    ва
    0.78
    0.78
     그래도
    0.77
     ObjectId
    0.76
     Hausdorff
    0.75
    soever
    0.74
    POSITIVE LOGITS
    il
    1.01
    ج
    0.87
     volle
    0.78
    МО
    0.73
    மாகக்
    0.72
     spic
    0.71
     MO
    0.71
     celor
    0.71
     kaik
    0.71
     შორის
    0.70
    Act Density 0.410%

    No Known Activations