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

    Neuronpedia

    INDEX
    Explanations

    ingredients and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    այի
    0.65
    at
    0.63
    r
    0.57
    arms
    0.55
     měl
    0.55
     THIS
    0.54
     sparen
    0.54
    跟
    0.54
    猁
    0.54
    atthe
    0.53
    POSITIVE LOGITS
    ка
    0.63
     de
    0.56
     т
    0.55
    도
    0.55
     ت
    0.54
     کوردستان
    0.53
     د
    0.52
     کورد
    0.51
    را
    0.50
    ید
    0.50
    Act Density 0.024%

    No Known Activations