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

    Neuronpedia

    INDEX
    Explanations

    raise questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tendency
    0.41
     approach
    0.36
     progression
    0.35
     Phrases
    0.35
     從
    0.35
     incline
    0.35
    াসা
    0.34
     deviation
    0.34
     Approach
    0.34
    ascending
    0.33
    POSITIVE LOGITS
     questions
    1.14
     issues
    0.99
     вопросы
    0.97
    questions
    0.91
     вопросов
    0.90
     frågor
    0.88
    issues
    0.87
     सवाल
    0.86
     Fragen
    0.86
     questões
    0.85
    Act Density 0.007%

    No Known Activations