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

    Neuronpedia

    INDEX
    Explanations

    Catalan/Spanish place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    1.16
    ↵
    1.05
    c
    1.05
    g
    1.03
    i
    1.02
    ia
    0.97
    a
    0.96
    ק
    0.94
    ihe
    0.92
    as
    0.89
    POSITIVE LOGITS
    .
    0.98
    ਰ
    0.98
    지만
    0.95
    好
    0.94
    いる
    0.89
    ות
    0.89
    টি
    0.88
     it
    0.87
    ים
    0.86
    时候
    0.85
    Act Density 0.000%

    No Known Activations