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

    Neuronpedia

    INDEX
    Explanations

    languages and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     करणाऱ्या
    0.29
    iere
    0.27
    fections
    0.25
    াধীন
    0.25
    ers
    0.25
    iation
    0.25
    ્ટ
    0.24
    enance
    0.24
    inerja
    0.24
    aterials
    0.24
    POSITIVE LOGITS
     তুমি
    0.39
     bạn
    0.38
     چې
    0.36
     você
    0.35
     sẽ
    0.35
    我們
    0.35
     ඔබට
    0.35
     നിങ്ങൾ
    0.35
    ที่จะ
    0.35
     പിന്നെ
    0.35
    Act Density 0.074%

    No Known Activations