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

    Neuronpedia

    INDEX
    Explanations

    comparisons and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मुकाब
    0.40
    eagle
    0.39
    Eagle
    0.39
    गेन
    0.38
    굿
    0.38
     সুখী
    0.37
    ूल
    0.37
     merciful
    0.36
    crown
    0.36
    飧
    0.36
    POSITIVE LOGITS
     នៅ
    0.43
     το
    0.41
     això
    0.41
     Nasr
    0.40
     ito
    0.40
     ለ
    0.38
    ہار
    0.38
     Landscapes
    0.38
     hayat
    0.38
     everything
    0.38
    Act Density 0.004%

    No Known Activations