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

    Neuronpedia

    INDEX
    Explanations

    infinitive verb phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ื่อ
    0.44
    клу
    0.42
    す楽
    0.42
    valid
    0.41
    ät
    0.41
    żu
    0.41
     ছয়
    0.40
    轻松
    0.40
    alarını
    0.40
    analy
    0.40
    POSITIVE LOGITS
     behold
    0.54
     आपल्याला
    0.46
     decirlo
    0.43
    angk
    0.43
    وار
    0.43
     mình
    0.43
     ninguém
    0.42
     mention
    0.41
     molte
    0.41
     لحاظ
    0.41
    Act Density 0.011%

    No Known Activations