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

    Neuronpedia

    INDEX
    Explanations

    observation or estimate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SAI
    0.41
    ।
    0.37
     nai
    0.37
     বক্তব্য
    0.36
    路径
    0.36
     (\<
    0.34
     lineWidth
    0.34
    妏
    0.34
     dimensión
    0.33
     sahiptir
    0.33
    POSITIVE LOGITS
    et
    0.39
    imbo
    0.38
    क्रामक
    0.37
     അയാൾ
    0.37
    apartment
    0.37
    adjustment
    0.36
    otro
    0.36
    ale
    0.36
     menacing
    0.35
    ür
    0.34
    Act Density 0.000%

    No Known Activations