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

    Neuronpedia

    INDEX
    Explanations

    question/inquiry in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zov
    0.38
    സ
    0.37
    mm
    0.36
     ấy
    0.35
    right
    0.35
    führer
    0.35
    Authorized
    0.35
    দাতা
    0.34
    도가
    0.34
      
    0.34
    POSITIVE LOGITS
     pertanyaan
    0.50
     pergunta
    0.46
     dSample
    0.43
    PerTrial
    0.42
     spør
    0.41
     soru
    0.41
     fromi
    0.40
    ्यानंतर
    0.40
    ꯤ
    0.39
     vragen
    0.39
    Act Density 0.000%

    No Known Activations