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

    Neuronpedia

    INDEX
    Explanations

    late 2023/early 2024

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    0.91
    ла
    0.89
    ма
    0.86
    ça
    0.85
    he
    0.84
    ère
    0.80
    ésére
    0.76
    ść
    0.76
    ča
    0.75
    ó
    0.75
    POSITIVE LOGITS
     boyunca
    0.87
     dues
    0.79
     Edu
    0.78
     XLSX
    0.76
     emojis
    0.73
     afresh
    0.73
     mendatang
    0.72
     الدراسي
    0.72
    ಧ್ಯ
    0.71
     equips
    0.71
    Act Density 0.073%

    No Known Activations