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

    Neuronpedia

    INDEX
    Explanations

    la ending sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nya
    2.93
    ly
    2.46
    n
    2.24
    க்
    2.17
    م
    2.06
    shire
    1.90
    ことが
    1.88
    ness
    1.87
    ই
    1.85
    न
    1.81
    POSITIVE LOGITS
    verick
    1.73
     sera
    1.64
    ً
    1.58
    ूहिक
    1.54
    普通的
    1.52
    ulkner
    1.52
    ɖ
    1.51
    жды
    1.48
    şı
    1.47
    qué
    1.46
    Act Density 0.091%

    No Known Activations