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

    Neuronpedia

    INDEX
    Explanations

    tables and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ພາ
    0.41
    దవ
    0.41
    欧元
    0.39
    inee
    0.39
    rzej
    0.38
    лит
    0.38
    िल्म
    0.38
     கழு
    0.37
    dotto
    0.36
    ıyla
    0.35
    POSITIVE LOGITS
     grid
    0.41
     tabular
    0.40
     tabel
    0.39
     subgroup
    0.38
     table
    0.38
     grids
    0.38
     GRID
    0.38
     tables
    0.37
    場合
    0.37
     तालिका
    0.37
    Act Density 0.000%

    No Known Activations