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

    Neuronpedia

    INDEX
    Explanations

    phonetic transcriptions of sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cantidad
    0.44
     тамо
    0.43
    yorum
    0.42
    нее
    0.42
     Yesu
    0.41
     নাঁ
    0.41
     আল্লাহ
    0.40
    悰
    0.40
     vaya
    0.40
    फिया
    0.40
    POSITIVE LOGITS
    ə
    0.59
    ɪ
    0.54
    ɚ
    0.50
     /ˈ
    0.49
    mə
    0.48
     (/
    0.46
    ˈ
    0.46
    ˌ
    0.46
     wanna
    0.45
    ɹ
    0.45
    Act Density 0.013%

    No Known Activations