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

    Neuronpedia

    INDEX
    Explanations

    mixing and listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    okość
    0.55
     প্রার্থনা
    0.54
     제출
    0.50
    ИС
    0.50
    ਿੰ
    0.49
     पूर्वक
    0.47
    িয়ন
    0.46
     |”
    0.46
    τους
    0.46
    \"{
    0.46
    POSITIVE LOGITS
     combine
    0.45
     elevado
    0.45
     hilo
    0.43
     and
    0.43
    性和
    0.41
     druga
    0.40
     additions
    0.40
     map
    0.39
     mix
    0.39
     vantagens
    0.39
    Act Density 0.010%

    No Known Activations