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

    Neuronpedia

    INDEX
    Explanations

    vowel sounds followed by consonant sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    으로
    0.50
    ानि
    0.45
    ів
    0.44
    uanya
    0.44
    ıştır
    0.44
    ार्थ
    0.43
    ahorse
    0.43
    ът
    0.42
    ிகளை
    0.42
    ێت
    0.42
    POSITIVE LOGITS
    ze
    0.69
    zer
    0.65
    zle
    0.64
    zy
    0.63
    zes
    0.60
    zers
    0.58
    ̆
    0.53
    зы
    0.52
    ̯
    0.52
    za
    0.51
    Act Density 0.026%

    No Known Activations