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

    Neuronpedia

    INDEX
    Explanations

    numbers and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াবিশ
    0.45
    क्ताओं
    0.41
     distingue
    0.41
    etur
    0.38
    চ্ছ
    0.38
     ငါ
    0.38
     varía
    0.37
     distinguir
    0.37
     বাহিনী
    0.37
     equivariant
    0.37
    POSITIVE LOGITS
    סק
    0.42
    тин
    0.41
     PRESENT
    0.41
    ⓜ
    0.39
     mengisi
    0.39
    âmara
    0.39
    пи
    0.38
    ש
    0.38
    欝
    0.38
     brush
    0.37
    Act Density 0.000%

    No Known Activations