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

    Neuronpedia

    INDEX
    Explanations

    describing actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     можете
    0.60
    בה
    0.57
     DevOps
    0.57
     omnichannel
    0.56
     gründ
    0.55
     Unternehmen
    0.54
    Привет
    0.54
     ChatGPT
    0.54
     FAQs
    0.54
    🏆
    0.54
    POSITIVE LOGITS
    this
    0.71
     هذا
    0.70
    lemish
    0.69
    orescent
    0.66
    necklace
    0.66
    仿佛
    0.65
     sogen
    0.65
     sogenannte
    0.61
    question
    0.60
     احد
    0.60
    Act Density 0.091%

    No Known Activations